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

    Neuronpedia

    INDEX
    Explanations

    bonuses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Normdatei
    -1.20
    principalColumn
    -1.12
    GEBURTSDATUM
    -1.12
    WithIOException
    -1.09
    MessageTagHelper
    -1.03
    Geplaatst
    -1.02
    Билгалдахарш
    -1.02
    verwijspagina
    -1.00
    出版年
    -0.97
     Roskov
    -0.96
    POSITIVE LOGITS
    es
    0.58
    y
    0.56
    .
    0.52
    hh
    0.50
     local
    0.48
     the
    0.47
     non
    0.47
    ,
    0.47
     are
    0.46
     basic
    0.46
    Act Density 0.064%

    No Known Activations