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

    Neuronpedia

    INDEX
    Explanations

    constructor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pu
    -0.06
     Stop
    -0.06
     Hasan
    -0.06
     baj
    -0.06
     Это
    -0.06
     media
    -0.06
     xrange
    -0.06
     ruined
    -0.06
    Explicit
    -0.06
     desi
    -0.06
    POSITIVE LOGITS
    eldorf
    0.08
     Carr
    0.07
     потрібно
    0.07
    箱
    0.07
    _CONTINUE
    0.06
     چرخ
    0.06
     lifestyles
    0.06
    初始化
    0.06
    不知
    0.06
     scorer
    0.06
    Act Density 0.001%

    No Known Activations