INDEX

Explanations

drug delivery

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

code and technical documentation comments, headers, and formatting lines.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

This neuron spots section or comment “divider” lines—i.e. long runs of the same punctuation (dashes, asterisks, etc.) or other markers used to separate parts of code or comments.

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

Negative Logits

you

-1.44

toDouble

-1.33

๕

-1.19

aktifkan

-1.18

yym

-1.17

 implique

-1.16

 susceptibility

-1.16

centerTitle

-1.16

 belge

-1.14

朕

-1.13

POSITIVE LOGITS

。）

1.16

 Präsentation

1.10

or

1.10

 präsenti

1.09

which

1.08

 Sortiment

1.05

1.02

앓

1.02

0.98

Activations Density 0.000%

drug delivery

code and technical documentation comments, headers, and formatting lines.

This neuron spots section or comment “divider” lines—i.e. long runs of the same punctuation (dashes, asterisks, etc.) or other markers used to separate parts of code or comments.

No Known Activations

drug delivery

code and technical documentation comments, headers, and formatting lines.

This neuron spots section or comment “divider” lines—i.e. long runs of the same punctuation (dashes, asterisks, etc.) or other markers used to separate parts of code or comments.

No Known Activations