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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reluctantly
    -0.08
    測
    -0.06
     mnoha
    -0.06
     určitě
    -0.06
    (period
    -0.06
     strtol
    -0.06
    _DEST
    -0.06
     worries
    -0.06
    шку
    -0.06
     ▲
    -0.06
    POSITIVE LOGITS
    aha
    0.06
    erguson
    0.06
    는
    0.06
     GTK
    0.06
    ação
    0.06
    _disk
    0.06
    نتی
    0.06
    <↵
    0.06
     privileges
    0.06
    \u
    0.06
    Act Density 0.001%

    No Known Activations