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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تماع
    -0.06
    {}'.
    -0.06
     thighs
    -0.06
    .minute
    -0.06
     Calif
    -0.06
    �
    -0.06
    Blo
    -0.06
    Instead
    -0.06
     вважа
    -0.06
    Numero
    -0.06
    POSITIVE LOGITS
    hya
    0.07
     Pvt
    0.06
    .linspace
    0.06
     hopes
    0.06
    检测
    0.06
     піс
    0.06
     airborne
    0.06
    (payment
    0.06
    _motor
    0.06
    елен
    0.06
    Act Density 0.005%

    No Known Activations