INDEX

Explanations

code tokens and punctuation

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

The neuron is picking out non‐natural-language “markup” tokens—things like HTML entities (e.g.  ), punctuation‐heavy link or code fragments, URLs, and uppercase acronyms.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

of

-2.39

it

-1.88

on

-1.57

had

-1.54

for

-1.52

 with

-1.36

 />';

-1.34

out

-1.33

-1.28

 while

-1.27

POSITIVE LOGITS

ꟷ

1.46

 ruines

1.45

othes

1.41

があり

1.38

があるので

1.36

以及

1.34

 quelques

1.34

还有

1.33

などが

1.33

 firs

1.29

Activations Density 0.034%

code tokens and punctuation

The neuron is picking out non‐natural-language “markup” tokens—things like HTML entities (e.g.  ), punctuation‐heavy link or code fragments, URLs, and uppercase acronyms.

No Comments

No Known Activations

code tokens and punctuation

The neuron is picking out non‐natural-language “markup” tokens—things like HTML entities (e.g.  ), punctuation‐heavy link or code fragments, URLs, and uppercase acronyms.

No Comments

No Known Activations

code tokens and punctuation

The neuron is picking out non‐natural-language “markup” tokens—things like HTML entities (e.g. &nbsp;), punctuation‐heavy link or code fragments, URLs, and uppercase acronyms.

No Comments

No Known Activations

code tokens and punctuation

The neuron is picking out non‐natural-language “markup” tokens—things like HTML entities (e.g. &nbsp;), punctuation‐heavy link or code fragments, URLs, and uppercase acronyms.

No Comments

No Known Activations

The neuron is picking out non‐natural-language “markup” tokens—things like HTML entities (e.g. ), punctuation‐heavy link or code fragments, URLs, and uppercase acronyms.

The neuron is picking out non‐natural-language “markup” tokens—things like HTML entities (e.g. ), punctuation‐heavy link or code fragments, URLs, and uppercase acronyms.