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

    Neuronpedia

    INDEX
    Explanations

    Animal sex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    支持
    -0.07
     Sta
    -0.06
    IGNAL
    -0.06
     kir
    -0.06
    (amount
    -0.06
    arda
    -0.06
    .reply
    -0.06
     unanim
    -0.06
    _support
    -0.06
    rane
    -0.06
    POSITIVE LOGITS
     ngọt
    0.07
    ีว
    0.06
    .Pre
    0.06
     infring
    0.06
    .'
    0.06
     Пр
    0.06
    -of
    0.06
    )init
    0.06
    toBeInTheDocument
    0.06
     şar
    0.06
    Act Density 0.135%

    No Known Activations