INDEX

Explanations

electroretinographic

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

fields containing descriptions in structured data formats or documentation.

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

Triggered by @neilrathi

The neuron fires on quoted description or content text values (e.g. metadata “description” or “content” fields) in JSON or HTML.

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

 where

-1.11

in

-0.99

 both

-0.94

on

-0.94

all

-0.90

Banner

-0.88

 事業

-0.87

 mogę

-0.86

 these

-0.84

 those

-0.84

POSITIVE LOGITS

 появится

1.08

throughout

1.05

 inond

1.00

malte

0.98

ﺳ

0.97

Портали

0.96

ﻣ

0.95

Ekster

0.94

ising

0.93

ſes

0.93

Activations Density 0.000%

electroretinographic

fields containing descriptions in structured data formats or documentation.

The neuron fires on quoted description or content text values (e.g. metadata “description” or “content” fields) in JSON or HTML.

No Known Activations

electroretinographic

fields containing descriptions in structured data formats or documentation.

The neuron fires on quoted description or content text values (e.g. metadata “description” or “content” fields) in JSON or HTML.

No Known Activations