INDEX

Explanations

documentation sections and keywords

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

markdown headings (lines starting with `##`).

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

The neuron specializes in spotting numeric tokens (especially numbers in headings or section markers) and outputs their numeric value.

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

畀

-1.54

for

-1.44

 البته

-1.41

了一个

-1.39

出了一

-1.30

ervazione

-1.30

влено

-1.30

ouml

-1.30

了一眼

-1.29

 then

-1.28

POSITIVE LOGITS

 mutiara

1.72

 medlems

1.55

 після

1.49

 these

1.46

 ($("#

1.44

 tabung

1.43

 aktivitet

1.41

 skrift

1.40

ньому

1.39

 kanak

1.39

Activations Density 0.001%

documentation sections and keywords

markdown headings (lines starting with `##`).

The neuron specializes in spotting numeric tokens (especially numbers in headings or section markers) and outputs their numeric value.

No Comments

No Known Activations

documentation sections and keywords

markdown headings (lines starting with `##`).

The neuron specializes in spotting numeric tokens (especially numbers in headings or section markers) and outputs their numeric value.

No Comments

No Known Activations