INDEX

Explanations

inducible, inductively, inducer

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

The neuron detects forms of the word "induce," particularly the variations "inducible" and "inductively" in scientific contexts.

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

The neuron consistently activates on the word‐fragment “indu,” marking occurrences of terms derived from the root “indu” (e.g., induce, induction, inducible).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/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

ypos

-0.78

笔记本

-0.74

 zupełnie

-0.73

저

-0.72

@__

-0.71

 grafico

-0.70

 FOREIGN

-0.70

urther

-0.70

 emblema

-0.69

 habrían

-0.69

POSITIVE LOGITS

IZIONE

0.80

Platz

0.78

容

0.74

 одну

0.72

Después

0.71

ıld

0.70

included

0.69

机器

0.69

tière

0.69

Pek

0.68

Activations Density 0.051%

inducible, inductively, inducer

The neuron detects forms of the word "induce," particularly the variations "inducible" and "inductively" in scientific contexts.

The neuron consistently activates on the word‐fragment “indu,” marking occurrences of terms derived from the root “indu” (e.g., induce, induction, inducible).

No Comments

No Known Activations

inducible, inductively, inducer

The neuron detects forms of the word "induce," particularly the variations "inducible" and "inductively" in scientific contexts.

The neuron consistently activates on the word‐fragment “indu,” marking occurrences of terms derived from the root “indu” (e.g., induce, induction, inducible).

No Comments

No Known Activations