Add hard_shrink activation function

[shashaka]

Since Keras lacks built-in support for the hard_shrink activation function, I implemented it across TensorFlow, JAX, and NumPy, aiming to maintain consistency with existing implementations available in PyTorch.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 88.57143% with 4 lines in your changes missing coverage. Please review.

Project coverage is 82.08%. Comparing base (8409e18) to head (9b18493).

Files with missing lines	Patch %	Lines
keras/api/_tf_keras/keras/activations/__init__.py	0.00%	1 Missing ⚠️
keras/api/_tf_keras/keras/ops/__init__.py	0.00%	1 Missing ⚠️
keras/api/_tf_keras/keras/ops/nn/__init__.py	0.00%	1 Missing ⚠️
keras/src/ops/nn.py	92.30%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##           master   #20470   +/-   ##
=======================================
  Coverage   82.07%   82.08%           
=======================================
  Files         515      515           
  Lines       47416    47451   +35     
  Branches     7439     7440    +1     
=======================================
+ Hits        38919    38950   +31     
- Misses       6691     6695    +4     
  Partials     1806     1806           

Flag	Coverage Δ
keras	81.93% <88.57%> (+<0.01%)	⬆️
keras-jax	65.01% <68.57%> (+<0.01%)	⬆️
keras-numpy	59.97% <74.28%> (+0.01%)	⬆️
keras-tensorflow	66.03% <65.71%> (-0.01%)	⬇️
keras-torch	64.93% <68.57%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.