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

    Neuronpedia

    INDEX
    Explanations

    number base conversions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帆
    -0.73
    znam
    -0.72
     summer
    -0.72
    sects
    -0.71
    Ộ
    -0.71
    зик
    -0.70
    舟
    -0.70
     フロ
    -0.69
    kops
    -0.69
    jong
    -0.68
    POSITIVE LOGITS
     decimal
    3.14
    decimal
    2.64
     Decimal
    2.63
    Decimal
    2.34
     dec
    2.22
     binary
    2.16
    dec
    2.11
     hex
    2.05
     oct
    1.93
    Dec
    1.91
    Act Density 0.075%

    No Known Activations