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

    Neuronpedia

    INDEX
    Explanations

    diverse text sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.79
    /**
    -0.77
    SourceChecksum
    -0.75
    Personensuche
    -0.72
     disambiguazione
    -0.71
     ویکی‌پدی
    -0.71
    LookAnd
    -0.69
    Chham
    -0.65
     ExecuteAsync
    -0.65
    ValueStyle
    -0.62
    POSITIVE LOGITS
     our
    0.51
     conf
    0.51
     belong
    0.51
     CONF
    0.51
    gatan
    0.50
     dependable
    0.49
     open
    0.49
    sson
    0.48
     Murray
    0.48
    ראות
    0.48
    Act Density 1.595%

    No Known Activations