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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cake
    -0.08
    .keyword
    -0.06
     reflect
    -0.06
    ождение
    -0.06
    flowers
    -0.06
    codile
    -0.06
     сна
    -0.06
     diagon
    -0.06
    تبة
    -0.06
    Remember
    -0.06
    POSITIVE LOGITS
    /Home
    0.06
     llen
    0.06
     dfs
    0.06
    partners
    0.06
     Bers
    0.06
    .mkdirs
    0.06
    .partner
    0.06
     zorunlu
    0.06
     صفحه
    0.06
     bufio
    0.06
    Act Density 0.002%

    No Known Activations