INDEX

Explanations

pandas operations like drop, groupby, concat

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

the word "drop" or method calls containing "drop" in programming contexts.

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

The neuron is detecting mentions of pandas DataFrame method calls (e.g. groupby, agg, drop, drop_duplicates, reset_index, apply).

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

 maybe

-1.86

if

-1.78

do

-1.66

).

-1.63

to

-1.63

}$.

-1.61

 others

-1.61

may

-1.57

 provide

-1.56

珦

-1.55

POSITIVE LOGITS

 sehe

1.94

 夜景

1.80

慙

1.76

襌

1.74

ーズン

1.73

 inan

1.70

 perles

1.69

豋

1.66

 ragaz

1.66

 gekocht

1.66

Activations Density 0.003%

pandas operations like drop, groupby, concat

the word "drop" or method calls containing "drop" in programming contexts.

The neuron is detecting mentions of pandas DataFrame method calls (e.g. groupby, agg, drop, drop_duplicates, reset_index, apply).

No Comments

No Known Activations

pandas operations like drop, groupby, concat

the word "drop" or method calls containing "drop" in programming contexts.

The neuron is detecting mentions of pandas DataFrame method calls (e.g. groupby, agg, drop, drop_duplicates, reset_index, apply).

No Comments

No Known Activations