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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    发表于
    -0.54
    dropIfExists
    -0.50
    Pulitzer
    -0.44
    ogener
    -0.41
    PopupWindow
    -0.41
    cerpt
    -0.40
     retras
    -0.39
     DriverManager
    -0.38
    roskop
    -0.38
    конец
    -0.38
    POSITIVE LOGITS
     am
    0.72
    contentLoaded
    0.66
     pm
    0.63
    Datuak
    0.61
    amc
    0.59
     tristesse
    0.59
    شنبه
    0.59
     nonatomic
    0.58
    am
    0.56
    Am
    0.56
    Act Density 0.003%

    No Known Activations