Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    roles after the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     발생
    0.64
     자료
    0.64
     관련
    0.63
    imetric
    0.62
     모습
    0.62
     مرتبط
    0.60
    usiasm
    0.59
     종합
    0.59
     콘텐츠
    0.58
    ผ้า
    0.58
    POSITIVE LOGITS
     recipient
    1.29
     wearer
    1.14
     unsuspecting
    1.13
     user
    1.10
     claimant
    1.08
     occupants
    1.08
     owner
    1.08
     interviewer
    1.07
     users
    1.07
     recipients
    1.06
    Act Density 0.409%

    No Known Activations