INDEX

Explanations

viruses and diseases

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

text about infectious diseases and their spread, particularly viruses like COVID-19.

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

Triggered by @neilrathi

This neuron detects factual statements about disease spread and related epidemiological statistics.

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

 configurações

-0.94

 angeschlossen

-0.93

for

-0.91

 those

-0.90

 оказался

-0.90

 vuestra

-0.90

 حتی

-0.89

結局

-0.89

alians

-0.88

 lantaran

-0.88

POSITIVE LOGITS

 coronavirus

1.23

 COVID

1.23

 visuelle

1.17

estão

1.05

 السياس

1.04

 cammin

1.01

RIQUE

0.99

τικός

0.99

 itinéraire

0.98

\%,

0.98

Activations Density 0.027%

viruses and diseases

text about infectious diseases and their spread, particularly viruses like COVID-19.

This neuron detects factual statements about disease spread and related epidemiological statistics.

No Known Activations

viruses and diseases

text about infectious diseases and their spread, particularly viruses like COVID-19.

This neuron detects factual statements about disease spread and related epidemiological statistics.

No Known Activations