diff --git a/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.ipynb b/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.ipynb
index aba54b8c..803602ea 100644
--- a/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.ipynb
+++ b/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.ipynb
@@ -254,6 +254,7 @@
     "\n",
     "    return snapshot\n",
     "\n",
+    "\n",
     "system = System()\n",
     "snap = get_snap(system)\n",
     "snap = post_process_pos(snap)\n",
@@ -319,7 +320,7 @@
     ")\n",
     "periodic_params = dict(\n",
     "    A = dict(A = 0.5, i = 0, w = 0.2, p = 2),\n",
-    "    B = dict(A = 0.0, i = 0, w = 0.2, p = 1),\n",
+    "    B = dict(A = 0.0, i = 0, w = 0.02, p = 1),\n",
     ")\n",
     "\n",
     "def generate_simulation(\n",
@@ -403,7 +404,7 @@
    },
    "source": [
     "The next parameters we need to define and run the method are the harmonic biasing spring constant,\n",
-    "(which we set to to $50$), the log frequency for the histogram ($50$), the number of steps we discard\n",
+    "(which we set to to $100$), the log frequency for the histogram ($50$), the number of steps we discard\n",
     "as equilibration before logging ($10^3$), and the number of time steps per replica ($10^4$).\n",
     "\n",
     "Since this runs multiple simulations, we expect the next cell to execute for a while."
@@ -1028,7 +1029,7 @@
     }
    ],
    "source": [
-    "method = UmbrellaIntegration(cvs, 50.0, centers, 50, int(1e3))\n",
+    "method = UmbrellaIntegration(cvs, 100.0, centers, 50, int(1e3))\n",
     "raw_result = pysages.run(method, generate_simulation, int(1e4))\n",
     "result = pysages.analyze(raw_result)"
    ]
@@ -1070,7 +1071,7 @@
    "source": [
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "bins =50\n",
+    "bins = 50\n",
     "\n",
     "fig, ax = plt.subplots(2, 2)\n",
     "\n",
@@ -1147,7 +1148,7 @@
     "def external_field(r, A, p, w, **kwargs):\n",
     "    return A * np.tanh(1 / (2 * np.pi * p * w) * np.cos(p * r))\n",
     "\n",
-    "x = np.linspace(-2, 2, 50)\n",
+    "x = np.linspace(-2, 2, 100)\n",
     "data = external_field(x, **periodic_params[\"A\"])\n",
     "\n",
     "centers = np.asarray(result[\"centers\"])\n",
diff --git a/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.md b/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.md
index 14c08246..e34ab57f 100644
--- a/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.md
+++ b/examples/hoomd-blue/umbrella_integration/Umbrella_Integration.md
@@ -122,6 +122,7 @@ def get_snap(system):
 
     return snapshot
 
+
 system = System()
 snap = get_snap(system)
 snap = post_process_pos(snap)
@@ -156,7 +157,7 @@ dpd_params = dict(
 )
 periodic_params = dict(
     A = dict(A = 0.5, i = 0, w = 0.2, p = 2),
-    B = dict(A = 0.0, i = 0, w = 0.2, p = 1),
+    B = dict(A = 0.0, i = 0, w = 0.02, p = 1),
 )
 
 def generate_simulation(
@@ -211,14 +212,14 @@ centers = list(np.linspace(-1.5, 1.5, 25))
 
 <!-- #region id="q37sUT-tbOMS" -->
 The next parameters we need to define and run the method are the harmonic biasing spring constant,
-(which we set to to $50$), the log frequency for the histogram ($50$), the number of steps we discard
+(which we set to to $100$), the log frequency for the histogram ($50$), the number of steps we discard
 as equilibration before logging ($10^3$), and the number of time steps per replica ($10^4$).
 
 Since this runs multiple simulations, we expect the next cell to execute for a while.
 <!-- #endregion -->
 
 ```python colab={"base_uri": "https://localhost:8080/"} id="wIrPB2N0bFIl" outputId="2f018685-a115-4c66-a21a-eef1d515bd02"
-method = UmbrellaIntegration(cvs, 50.0, centers, 50, int(1e3))
+method = UmbrellaIntegration(cvs, 100.0, centers, 50, int(1e3))
 raw_result = pysages.run(method, generate_simulation, int(1e4))
 result = pysages.analyze(raw_result)
 ```
@@ -230,7 +231,7 @@ What is left after the run is evaluating the resulting histograms for each of th
 ```python colab={"base_uri": "https://localhost:8080/", "height": 265} id="OOpagwvlb3_d" outputId="62b507a1-d404-4924-ec1b-00b9d3f39085"
 import matplotlib.pyplot as plt
 
-bins =50
+bins = 50
 
 fig, ax = plt.subplots(2, 2)
 
@@ -267,7 +268,7 @@ And finally, as the last step, we can visualize the estimated free-energy path f
 def external_field(r, A, p, w, **kwargs):
     return A * np.tanh(1 / (2 * np.pi * p * w) * np.cos(p * r))
 
-x = np.linspace(-2, 2, 50)
+x = np.linspace(-2, 2, 100)
 data = external_field(x, **periodic_params["A"])
 
 centers = np.asarray(result["centers"])