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

    Neuronpedia

    INDEX
    Explanations

    say "See"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    juries
    -0.08
     дорог
    -0.07
    VectorXd
    -0.07
    金融服务
    -0.07
    onomous
    -0.07
    -approved
    -0.07
     бизнес
    -0.07
    <Cell
    -0.07
    ᐈ
    -0.07
    数字化
    -0.07
    POSITIVE LOGITS
    cw
    0.06
     ASSERT
    0.06
     Aly
    0.06
    _highlight
    0.06
    ivalent
    0.06
     ':
    0.06
    (${
    0.06
    _passed
    0.06
    קבוצה
    0.06
    不理
    0.06
    Act Density 0.001%

    No Known Activations