INDEX

Explanations

code

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

whitespace indentation at the beginning of lines in code, particularly indicating nested code blocks.

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

This neuron picks out numeric literals (numbers) in the 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

脔

-1.83

</td>

-1.81

之前

-1.70

หรือ

-1.70

これは

-1.67

Основ

-1.65

Sprache

-1.64

或者

-1.63

蚡

-1.63

艄

-1.62

POSITIVE LOGITS

1.91

in

1.88

and

1.87

to

1.77

at

1.73

方には

1.49

 between

1.48

に住

1.47

 وذلك

1.46

Activations Density 0.028%

code

whitespace indentation at the beginning of lines in code, particularly indicating nested code blocks.

This neuron picks out numeric literals (numbers) in the code.

No Comments

No Known Activations

code

whitespace indentation at the beginning of lines in code, particularly indicating nested code blocks.

This neuron picks out numeric literals (numbers) in the code.

No Comments

No Known Activations