INDEX

Explanations

command arguments or string literals

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

opening quotation marks in command-line scripts and code.

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

The neuron is strongly activated by double‐quote characters (i.e. it detects occurrences of “).

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

tne

-1.53

création

-1.52

scream

-1.48

 디자인

-1.47

scc

-1.44

slime

-1.43



-1.42

办

-1.41

 versus

-1.41

 δεν

-1.40

POSITIVE LOGITS

</u>

2.13

 في

1.79

」

1.78

în

1.76

ITY

1.74

 gustar

1.73

</i>

1.73

 nelle

1.66

 miſ

1.65

в

1.64

Activations Density 0.048%

command arguments or string literals

opening quotation marks in command-line scripts and code.

The neuron is strongly activated by double‐quote characters (i.e. it detects occurrences of “).

No Comments

No Known Activations

command arguments or string literals

opening quotation marks in command-line scripts and code.

The neuron is strongly activated by double‐quote characters (i.e. it detects occurrences of “).

No Comments

No Known Activations