INDEX

Explanations

code comments or block delimiters

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

inline comments in code, particularly those explaining or annotating specific lines or sections.

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

The neuron fires on code‐comment markers (i.e. the "//" that begins comments 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

↵

-2.92

-2.00

-1.93

is

-1.78

-1.77

-1.75

ing

-1.74

推特

-1.71

some

-1.64

–

-1.63

POSITIVE LOGITS

蛰

1.98



1.91

貼

1.84

撷

1.83

腟

1.79

ﾚ

1.79

咔嚓

1.79

ైన

1.76

都不会

1.73

姆

1.73

Activations Density 0.004%

code comments or block delimiters

inline comments in code, particularly those explaining or annotating specific lines or sections.

The neuron fires on code‐comment markers (i.e. the "//" that begins comments in code).

No Comments

No Known Activations

code comments or block delimiters

inline comments in code, particularly those explaining or annotating specific lines or sections.

The neuron fires on code‐comment markers (i.e. the "//" that begins comments in code).

No Comments

No Known Activations