INDEX

Explanations

diseases and outbreaks

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

The neuron identifies infectious disease names and related terminology such as viruses, epidemics, and outbreaks.

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

The neuron detects mentions of specific infectious diseases or viruses (e.g. Swine Flu, H1N1, Ebola, Nipah, plague, dengue fever, SARS-CoV-2).

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

 based

-1.33

 גם

-1.30

for

-1.26

अप

-1.26

 also

-1.25

ks

-1.23

 też

-1.23

一个

-1.20

본

-1.20

也是

-1.18

POSITIVE LOGITS

Our

1.59

 naszego

1.58

 nuestras

1.48

 naszych

1.48

 debemos

1.48

 éstas

1.44

Andere

1.41

hender

1.41

 unsere

1.40

我們的

1.40

Activations Density 0.138%

diseases and outbreaks

The neuron identifies infectious disease names and related terminology such as viruses, epidemics, and outbreaks.

The neuron detects mentions of specific infectious diseases or viruses (e.g. Swine Flu, H1N1, Ebola, Nipah, plague, dengue fever, SARS-CoV-2).

No Comments

No Known Activations

diseases and outbreaks

The neuron identifies infectious disease names and related terminology such as viruses, epidemics, and outbreaks.

The neuron detects mentions of specific infectious diseases or viruses (e.g. Swine Flu, H1N1, Ebola, Nipah, plague, dengue fever, SARS-CoV-2).

No Comments

No Known Activations