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

    Neuronpedia

    INDEX
    Explanations

    unfair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <v
    -0.07
    遊戲
    -0.07
    Liv
    -0.06
    loser
    -0.06
     gameId
    -0.06
    *=*=
    -0.06
    =v
    -0.06
     resonance
    -0.06
    Activities
    -0.06
     tslint
    -0.06
    POSITIVE LOGITS
    太多
    0.08
     Artist
    0.07
    oji
    0.07
    /job
    0.07
    듸
    0.07
     בלי
    0.07
    卫浴
    0.06
    蹊
    0.06
    Ị
    0.06
    悄悄
    0.06
    Act Density 0.005%

    No Known Activations