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

    Neuronpedia

    INDEX
    Explanations

    existence/quantification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ment
    -0.08
     oppon
    -0.08
     kilku
    -0.07
     mocha
    -0.07
    upu
    -0.07
    �
    -0.07
     commiss
    -0.07
    /shop
    -0.07
     printed
    -0.07
    吊
    -0.07
    POSITIVE LOGITS
    _in
    0.08
     пыта
    0.08
     запуска
    0.08
    czy
    0.07
    кыл
    0.07
    erweise
    0.07
     billi
    0.07
     Cruc
    0.07
     считают
    0.07
     выполня
    0.07
    Act Density 0.106%

    No Known Activations