Add silu support, fix neural_nets typo

[dilpath]

The Dandekar problem uses the SiLU activation function, which is currently not in the documented list of supported functions.
https://github.com/sebapersson/Benchmark-Models-PEtab-SciML/blob/8fcc885dd3599fa1c536a7084993a7a522df343c/Benchmark-Models/Dandekar_Patterns2020/net1_Dandekar_Patterns2020.yaml#L31

[sebapersson]

Thanks, forgot this.

silu is at least supported in the test-suite, see PEtab-dev/petab_sciml_testsuite#36

[sebapersson]

Could you here highlight this activation function is also called swish, e.g., silu (swish), as it is called swish in Lux.jl?

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 95.13%. Comparing base (2ef0387) to head (70551c6).
⚠️ Report is 7 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #90      +/-   ##
==========================================
+ Coverage   94.01%   95.13%   +1.11%     
==========================================
  Files           6        7       +1     
  Lines         301      370      +69     
==========================================
+ Hits          283      352      +69     
  Misses         18       18              

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.