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

    Neuronpedia

    INDEX
    Explanations

    "requirements.txt" files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     borr
    -0.07
    星
    -0.06
    sız
    -0.06
    mb
    -0.06
     stubborn
    -0.06
     kolo
    -0.06
    _dim
    -0.06
     ček
    -0.06
     Norte
    -0.06
    事
    -0.06
    POSITIVE LOGITS
    quia
    0.07
    召
    0.06
     IDR
    0.06
    ,’
    0.06
    uyla
    0.06
    ********************************
    0.06
    ！」
    0.06
    wcsstore
    0.06
    atican
    0.06
    .").
    0.06
    Act Density 0.003%

    No Known Activations