From f86947c07bd4f2c04ce508dba76f88d4ea8e4bac Mon Sep 17 00:00:00 2001
From: Qian Zhang <88585542+QianZhang19@users.noreply.github.com>
Date: Tue, 18 Mar 2025 14:11:23 +0000
Subject: [PATCH] Backport PR #29767: Add description to logit_demo.py script

---
 galleries/examples/scales/logit_demo.py | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/galleries/examples/scales/logit_demo.py b/galleries/examples/scales/logit_demo.py
index 22a56433ccd7..e8d42fc35711 100644
--- a/galleries/examples/scales/logit_demo.py
+++ b/galleries/examples/scales/logit_demo.py
@@ -4,6 +4,20 @@
 ===========
 
 Examples of plots with logit axes.
+
+This example visualises how ``set_yscale("logit")`` works on probability plots
+by generating three distributions: normal, laplacian, and cauchy in one plot.
+
+The advantage of logit scale is that it effectively spreads out values close to 0 and 1.
+
+In a linear scale plot, probability values near 0 and 1 appear compressed,
+making it difficult to see differences in those regions.
+
+In a logit scale plot, the transformation expands these regions,
+making the graph cleaner and easier to compare across different probability values.
+
+This makes the logit scale especially useful when visalising probabilities in logistic
+regression, classification models, and cumulative distribution functions.
 """
 
 import math