INDEX

Explanations

DataFrame variable assignment

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

the character sequence "df" appearing in code, technical documentation, or data files.

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

The neuron is triggered by the token “df” (e.g. in file names, URLs, variable names, or hex-like 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

↵

-3.98

);

-3.03



-2.66

咵

-2.28

 hinsichtlich

-2.25

).

-2.22

 Herzens

-2.22

 好看

-2.22

回想

-2.19

咨

-2.19

POSITIVE LOGITS

 стал

2.91

after

2.81

ed

2.73

2.64

 perpé

2.61

はじめ

2.58

婓

2.58

 Elektronik

2.47

できれば

2.47

 cheering

2.47

Activations Density 0.014%

DataFrame variable assignment

the character sequence "df" appearing in code, technical documentation, or data files.

The neuron is triggered by the token “df” (e.g. in file names, URLs, variable names, or hex-like identifiers).

No Comments

No Known Activations

DataFrame variable assignment

the character sequence "df" appearing in code, technical documentation, or data files.

The neuron is triggered by the token “df” (e.g. in file names, URLs, variable names, or hex-like identifiers).

No Comments

No Known Activations