INDEX

Explanations

code unit tests

np_acts-logits-general · gemini-2.5-flash-lite

decorators or annotations that mark test methods or classes in unit testing code.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

This neuron detects test‐framework annotation or attribute markers (e.g. @Test, [TestMethod], [TestClass], [Theory], [InlineData], etc.).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 plainte

-1.69

 bibliothèque

-1.53

鹀

-1.51

Ꮸ

-1.48

 手绘

-1.47

características

-1.45

्ञ

-1.45

 inny

-1.42

___________

-1.38

 icône

-1.36

POSITIVE LOGITS

1.80

̗

1.77

 любы

1.71

illium

1.71

opheles

1.67

our

1.66

泐

1.66

 something

1.65

",

1.64

 太郎

1.64

Activations Density 0.003%

code unit tests

decorators or annotations that mark test methods or classes in unit testing code.

This neuron detects test‐framework annotation or attribute markers (e.g. @Test, [TestMethod], [TestClass], [Theory], [InlineData], etc.).

No Comments

No Known Activations

code unit tests

decorators or annotations that mark test methods or classes in unit testing code.

This neuron detects test‐framework annotation or attribute markers (e.g. @Test, [TestMethod], [TestClass], [Theory], [InlineData], etc.).

No Comments

No Known Activations