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

    Neuronpedia

    INDEX
    Explanations

    "do"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    do
    -1.06
    ser
    -0.79
    ly
    -0.79
    ness
    -0.77
    series
    -0.71
    go
    -0.70
    care
    -0.69
    teenth
    -0.63
    serie
    -0.62
    don
    -0.61
    POSITIVE LOGITS
    <bos>
    0.83
     CreateTagHelper
    0.75
    offsetof
    0.65
    TSCA
    0.60
    asonic
    0.57
    contentLoaded
    0.57
    onames
    0.57
     Roskov
    0.57
    anskje
    0.56
    Kesimpulan
    0.56
    Act Density 0.713%

    No Known Activations