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

    Neuronpedia

    INDEX
    Explanations

    law enforcement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    彼
    -0.07
     corridors
    -0.07
    驱
    -0.07
    apache
    -0.07
    iliği
    -0.07
     tended
    -0.07
    -X
    -0.06
    осуд
    -0.06
     corridor
    -0.06
    engu
    -0.06
    POSITIVE LOGITS
     "))↵
    0.06
     Eternal
    0.06
    咨
    0.06
     upro
    0.06
     الحي
    0.06
     Созд
    0.05
    査
    0.05
     jogador
    0.05
     Sung
    0.05
    %">↵
    0.05
    Act Density 0.045%

    No Known Activations