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

    Neuronpedia

    INDEX
    Explanations

    code/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ileceğini
    -0.07
     고개를
    -0.07
     Copenhagen
    -0.07
     constructor
    -0.06
    056
    -0.06
     wła
    -0.06
     Wiley
    -0.06
     Eaton
    -0.06
    Datas
    -0.06
    محمد
    -0.06
    POSITIVE LOGITS
    스템
    0.07
    ä
    0.06
    */↵↵
    0.06
    (any
    0.06
    __↵↵
    0.06
    Called
    0.06
    鉄道
    0.06
    oggler
    0.06
    {x
    0.06
     */
↵
↵
    0.06
    Act Density 0.081%

    No Known Activations