INDEX

Explanations

coronavirus pandemic

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

the word "coronavirus" and related terms like COVID-19.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron fires most strongly on occurrences of “coronavirus” (and related capitalizations), i.e. it detects mentions of the coronavirus/COVID-19 term.

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

皷

-2.42



-2.22

vignon

-2.22

⻬

-2.22

菹

-2.20

amplific

-2.17

 ersche

-2.16

 osserva

-2.14

 apoy

-2.11

劼

-2.11

POSITIVE LOGITS

it

2.91

–

2.55

le

2.52

<em>

2.52

for

2.44

2.31

＊

2.27

2.23

an

2.20

Activations Density 0.007%

coronavirus pandemic

the word "coronavirus" and related terms like COVID-19.

The neuron fires most strongly on occurrences of “coronavirus” (and related capitalizations), i.e. it detects mentions of the coronavirus/COVID-19 term.

No Comments

No Known Activations

coronavirus pandemic

the word "coronavirus" and related terms like COVID-19.

The neuron fires most strongly on occurrences of “coronavirus” (and related capitalizations), i.e. it detects mentions of the coronavirus/COVID-19 term.

No Comments

No Known Activations