INDEX

Explanations

use case

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

The neuron primarily activates on occurrences of the word “use” (especially in an imperative/instructional context).

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

instructional or technical text directing readers to use something, typically found in documentation, tutorials, or terms of service.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

statements about usage or utilization, especially explicit “use of/using” phrasing in instructional or legal contexts.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_31_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

 genutzt

0.65

ock

0.64

 acquis

0.64

用于

0.64

 USED

0.64

selves

0.63

ঃখ

0.61

Kao

0.61

ികിത്സ

0.60

于是

0.59

POSITIVE LOGITS

NewUrlParser

0.86

FUL

0.78

علم

0.72

डी

0.71

fulness

0.69

 xlink

0.69

寿命

0.69

कर्ता

0.68

到的

0.66

ابي

0.65

Activations Density 0.108%

use case

The neuron primarily activates on occurrences of the word “use” (especially in an imperative/instructional context).

instructional or technical text directing readers to use something, typically found in documentation, tutorials, or terms of service.

statements about usage or utilization, especially explicit “use of/using” phrasing in instructional or legal contexts.

No Comments

No Known Activations

use case

The neuron primarily activates on occurrences of the word “use” (especially in an imperative/instructional context).

instructional or technical text directing readers to use something, typically found in documentation, tutorials, or terms of service.

statements about usage or utilization, especially explicit “use of/using” phrasing in instructional or legal contexts.

No Comments

No Known Activations