INDEX

Explanations

Korean and Japanese object markers

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

This neuron detects non-English (especially East Asian) character tokens in the text.

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

Korean particles (을, 를) that mark direct objects in Korean sentences.

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

object-marking particles in Korean and Japanese text (e.g., nouns marked with the accusative case).

oai_token-act-pair · gpt-5 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

that

1.16

াই

0.90

and

0.89

out

0.89

っぽい

0.88

的一

0.84

least

0.83

wards

0.83

ंच

0.83

ע

0.83

POSITIVE LOGITS

 비롯

2.05

 위해

1.72

 통해

1.59

 위한

1.55

 위하여

1.38

 통해서

1.35

 위해서

1.23

 기준으로

1.23

 포함

1.23

 위해서는

1.20

Activations Density 0.001%

Korean and Japanese object markers

This neuron detects non-English (especially East Asian) character tokens in the text.

Korean particles (을, 를) that mark direct objects in Korean sentences.

object-marking particles in Korean and Japanese text (e.g., nouns marked with the accusative case).

No Comments

No Known Activations

Korean and Japanese object markers

This neuron detects non-English (especially East Asian) character tokens in the text.

Korean particles (을, 를) that mark direct objects in Korean sentences.

object-marking particles in Korean and Japanese text (e.g., nouns marked with the accusative case).

No Comments

No Known Activations