Enable the smooth version of spherical bessel functions in TensorNet

[kenko911]

Summary

Enable the smooth version of spherical Bessel functions in TensorNet, this is particularly important for the smoothness of trained PESs.

Checklist

• [x] Google format doc strings added. Check with ruff.
• [x] Type annotations included. Check with mypy.
• [x] Tests added for new features/fixes.
• [x] If applicable, new classes/functions/modules have duecredit @due.dcite decorators to reference relevant papers by DOI (example)

Tip: Install pre-commit hooks to auto-check types and linting before every commit:

pip install -U pre-commit
pre-commit install

[codecov[bot]]

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Comparison is base (12ded8c) 98.76% compared to head (0b31ac5) 98.80%.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #230 +/- ## ========================================== + Coverage 98.76% 98.80% +0.03% ========================================== Files 33 33 Lines 2748 2750 +2 ========================================== + Hits 2714 2717 +3 + Misses 34 33 -1 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.