INDEX

Explanations

medical, biological, and programming terms

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

references to lichen species and print/formatting functions in programming languages.

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

Triggered by @neilrathi

The neuron is detecting occurrences of the substring “lichen” (i.e. mentions of lichens or lichen-related terms).

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

Negative Logits

-4.38

-3.92

-3.56

-3.55

-3.33

-3.23

-3.03

ia

-2.97

-2.95

POSITIVE LOGITS

瑧

3.03

 geïsole

2.61

brazilian

2.58

 pagado

2.55

↑↑↑</

2.55

ilustra

2.55

nivea

2.53

bagno

2.53

 olvidado

2.53

 bekannte

2.53

Activations Density 0.001%

medical, biological, and programming terms

references to lichen species and print/formatting functions in programming languages.

The neuron is detecting occurrences of the substring “lichen” (i.e. mentions of lichens or lichen-related terms).

No Known Activations

medical, biological, and programming terms

references to lichen species and print/formatting functions in programming languages.

The neuron is detecting occurrences of the substring “lichen” (i.e. mentions of lichens or lichen-related terms).

No Known Activations