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

    Neuronpedia

    INDEX
    Explanations

    Code/gibberish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     оскільки
    -0.08
    ndl
    -0.07
     movers
    -0.07
     Creek
    -0.07
     поскольку
    -0.07
     medya
    -0.07
     Window
    -0.07
    'm
    -0.07
     ultimate
    -0.07
    gary
    -0.06
    POSITIVE LOGITS
    _BAD
    0.06
    <bits
    0.06
     chmod
    0.06
    漢
    0.06
     خط
    0.06
    ้้
    0.06
    157
    0.05
    enth
    0.05
     Produkt
    0.05
    /*****************************************************************************↵
    0.05
    Act Density 0.008%

    No Known Activations