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

    Neuronpedia

    INDEX
    Explanations

    the prefix "per-"

    oai_token-act-pair · gemini-2.0-flash

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.68
    GEBURTSDATUM
    -0.67
    Manbalar
    -0.66
    AutoScale
    -0.62
     للاسماء
    -0.60
     Beſ
    -0.59
     Roskov
    -0.58
    __(/*!
    -0.56
    XtraBars
    -0.55
    لينكات
    -0.55
    POSITIVE LOGITS
    ArgsConstructor
    0.54
     endwhile
    0.50
    awakeFromNib
    0.47
     BoxFit
    0.43
    ész
    0.42
    Heaven
    0.41
     跳转至
    0.40
    #![
    0.40
    ouille
    0.39
    GIVEREF
    0.39
    Act Density 0.899%

    No Known Activations