INDEX

Explanations

that/to followed by verbs or nouns

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

This neuron detects instances of people speaking or making requests—i.e. first-person or conversational speech and request verbs (asked, said, told, reminded, please, etc.).

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

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

0.63

 notoriously

0.59

 hapless

0.58

 건설

0.57

えています

0.56

 evidently

0.55

 通过

0.54

 unwitting

0.54

 bureaucrats

0.54

POSITIVE LOGITS

一定要

0.73

要在

0.73

হইবে

0.67

 secondo

0.67

と思った

0.67

foldername

0.67

 टेक्स्ट

0.67

｢

0.66

要去

0.66

তাহাকে

0.66

Activations Density 0.294%

that/to followed by verbs or nouns

This neuron detects instances of people speaking or making requests—i.e. first-person or conversational speech and request verbs (asked, said, told, reminded, please, etc.).

No Comments

No Known Activations

that/to followed by verbs or nouns

This neuron detects instances of people speaking or making requests—i.e. first-person or conversational speech and request verbs (asked, said, told, reminded, please, etc.).

No Comments

No Known Activations

**that/to followed by verbs or nouns**

This neuron detects instances of people speaking or making requests—i.e. first-person or conversational speech and request verbs (asked, said, told, reminded, please, etc.).

No Comments

No Known Activations

**that/to followed by verbs or nouns**

This neuron detects instances of people speaking or making requests—i.e. first-person or conversational speech and request verbs (asked, said, told, reminded, please, etc.).

No Comments

No Known Activations

that/to followed by verbs or nouns

that/to followed by verbs or nouns