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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _anim
    -0.06
    /gpio
    -0.06
     zas
    -0.06
    标题
    -0.06
    ौ
    -0.06
     inspectors
    -0.06
     celle
    -0.06
     UID
    -0.06
    _SPI
    -0.06
    079
    -0.06
    POSITIVE LOGITS
     taxpayer
    0.07
    レット
    0.06
    employed
    0.06
     Sc
    0.06
    ANCED
    0.06
     halinde
    0.06
     Sexy
    0.06
    XYZ
    0.06
     Р
    0.06
    payer
    0.06
    Act Density 0.002%

    No Known Activations