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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contests
    -0.08
     carga
    -0.07
     flexGrow
    -0.07
    ANA
    -0.07
    init
    -0.06
    _DEST
    -0.06
    ición
    -0.06
     práv
    -0.06
    <"
    -0.06
    """,↵
    -0.06
    POSITIVE LOGITS
     Schwar
    0.06
    封
    0.06
    즌
    0.06
     раствор
    0.06
     eligible
    0.06
     pré
    0.06
    吴
    0.06
    족
    0.06
     Мин
    0.06
    037
    0.06
    Act Density 0.033%

    No Known Activations