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

    Neuronpedia

    INDEX
    Explanations

    comparisons and alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Damien
    -0.08
    ोख
    -0.07
     рам
    -0.07
    チーム
    -0.06
     Jamie
    -0.06
    درس
    -0.06
     Auch
    -0.06
    胡
    -0.06
    クラブ
    -0.06
    ΕΡ
    -0.06
    POSITIVE LOGITS
     Setting
    0.07
    ei
    0.06
     compan
    0.06
    ียด
    0.06
    visualization
    0.06
     DatePicker
    0.06
    firstName
    0.06
     наблю
    0.06
    _CHARACTER
    0.06
    short
    0.06
    Act Density 0.287%

    No Known Activations