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

    Neuronpedia

    INDEX
    Explanations

    Energy physics radiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     panda
    -0.07
    汉子
    -0.07
    _pin
    -0.07
    _Pin
    -0.07
    dux
    -0.07
     sond
    -0.06
    经济学家
    -0.06
    /pi
    -0.06
     precis
    -0.06
    搞得
    -0.06
    POSITIVE LOGITS
     alternatives
    0.07
    ingredients
    0.07
    pto
    0.07
    읷
    0.07
     court
    0.07
    .transforms
    0.07
    же
    0.07
    permanent
    0.07
     California
    0.07
    hlen
    0.07
    Act Density 0.008%

    No Known Activations