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

    Neuronpedia

    INDEX
    Explanations

    truth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.07
     This
    -0.07
    ��
    -0.07
     ως
    -0.06
     parasites
    -0.06
    This
    -0.06
    隆
    -0.06
    ับค
    -0.06
     Filters
    -0.06
     çap
    -0.06
    POSITIVE LOGITS
    geom
    0.07
    (";
    0.07
     neue
    0.06
     oppressive
    0.06
    _hid
    0.06
     Alleg
    0.06
     Cors
    0.06
    _float
    0.06
     😉
    0.06
    "(
    0.06
    Act Density 0.462%

    No Known Activations