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

    Neuronpedia

    INDEX
    Explanations

    schemes, plotting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (activity
    -0.06
    getOption
    -0.06
    igkeit
    -0.06
    :");↵↵
    -0.06
     sıra
    -0.06
     Anda
    -0.06
    ��
    -0.06
    .N
    -0.06
    ))];↵
    -0.06
    :")↵
    -0.06
    POSITIVE LOGITS
     düz
    0.07
    declare
    0.07
    女子
    0.07
    die
    0.06
     lur
    0.06
     fooled
    0.06
     Due
    0.06
     quần
    0.06
     digits
    0.06
     거래
    0.06
    Act Density 0.019%

    No Known Activations