INDEX

Explanations

assigning classes

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

the word "class" in code, especially when assigning CSS classes or defining class attributes.

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

This neuron activates on occurrences of “class” (and variants like ClassName, classes, toggleClass, etc.) in code.

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

 with

-1.67

知る

-1.48

缡

-1.30

 Opportunities

-1.30

tallet

-1.28

",

-1.27

In

-1.27

↵↵↵

-1.27

 That

-1.27

POSITIVE LOGITS

 geheim

1.47

 Laat

1.41

 voila

1.40

 réalisateur

1.40

iyle

1.40

 Mijn

1.39

 Veel

1.37

 velg

1.35

льт

1.34

 新聞

1.34

Activations Density 0.024%

assigning classes

the word "class" in code, especially when assigning CSS classes or defining class attributes.

This neuron activates on occurrences of “class” (and variants like ClassName, classes, toggleClass, etc.) in code.

No Comments

No Known Activations

assigning classes

the word "class" in code, especially when assigning CSS classes or defining class attributes.

This neuron activates on occurrences of “class” (and variants like ClassName, classes, toggleClass, etc.) in code.

No Comments

No Known Activations