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

    Neuronpedia

    INDEX
    Explanations

    keys and guides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horsepower
    -0.07
    -0.07
     dims
    -0.07
    createElement
    -0.07
    웍
    -0.06
     ksz
    -0.06
     ulus
    -0.06
    icing
    -0.06
    _acl
    -0.06
    ugen
    -0.06
    POSITIVE LOGITS
    最初的
    0.08
    ﯻ
    0.07
    六大
    0.07
     حاجة
    0.06
     יה
    0.06
    .getHours
    0.06
    இ
    0.06
     aur
    0.06
    시험
    0.06
    ệnh
    0.06
    Act Density 0.054%

    No Known Activations