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

    Neuronpedia

    INDEX
    Explanations

    party

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _red
    -0.08
    ्�
    -0.07
    Ա
    -0.07
    新加
    -0.06
     ee
    -0.06
    登陆
    -0.06
     Suit
    -0.06
    鹔
    -0.06
    เส
    -0.06
    setColor
    -0.06
    POSITIVE LOGITS
     đảng
    0.07
     faz
    0.07
     Haram
    0.06
     ciudad
    0.06
    格尔
    0.06
     lumière
    0.06
     인간
    0.06
    ____
    0.06
    سرائيل
    0.06
    ыта
    0.06
    Act Density 0.012%

    No Known Activations