INDEX

Explanations

testing code

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

the word "Test" in code, particularly in class names, file paths, and method names.

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

This neuron fires on occurrences of “Test” (or “test”) in code—e.g. in class names, file names, or identifiers.

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

the

-1.45

tività

-1.35

 épaules

-1.34

辚

-1.29

æde

-1.28

áculo

-1.27

 offensi

-1.24

鮃

-1.22

ys

-1.17

tabolism

-1.16

POSITIVE LOGITS

</strong>

2.17

 литров

1.52

";

1.52

 tapasztal

1.52

 murale

1.52

also

1.49

 készült

1.49

1.48

 jego

1.47

찮

1.47

Activations Density 0.018%

testing code

the word "Test" in code, particularly in class names, file paths, and method names.

This neuron fires on occurrences of “Test” (or “test”) in code—e.g. in class names, file names, or identifiers.

No Comments

No Known Activations

testing code

the word "Test" in code, particularly in class names, file paths, and method names.

This neuron fires on occurrences of “Test” (or “test”) in code—e.g. in class names, file names, or identifiers.

No Comments

No Known Activations