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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turbulent
    -0.08
     turbulence
    -0.08
    .IOException
    -0.07
    .Runtime
    -0.07
    ustr
    -0.07
    iliar
    -0.07
    ensed
    -0.07
    _runtime
    -0.07
    <|reserved_200016|>
    -0.07
     garanti
    -0.07
    POSITIVE LOGITS
     हुन्छ
    0.09
    teis
    0.08
    हुँ
    0.08
     ցանկանում
    0.08
    吉
    0.08
     pursuant
    0.08
     раскры
    0.07
     —↵↵
    0.07
    alos
    0.07
    ேன்
    0.07
    Act Density 0.003%

    No Known Activations