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

    Neuronpedia

    INDEX
    Explanations

    Word formation and etymology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -circle
    -0.07
     Feature
    -0.07
    =['
    -0.07
    _probability
    -0.07
    行动
    -0.06
     dens
    -0.06
    里面
    -0.06
     출연
    -0.06
    <r
    -0.06
     bets
    -0.06
    POSITIVE LOGITS
    ']:↵
    0.07
    leigh
    0.06
     Sms
    0.06
    Boss
    0.06
     удив
    0.06
    .ToTable
    0.06
    fo
    0.06
    关键
    0.06
    (DWORD
    0.06
    лоп
    0.05
    Act Density 0.005%

    No Known Activations