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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.71
    HtmlAttribute
    -0.64
    SPJ
    -0.63
    Personensuche
    -0.60
    enumi
    -0.59
    RetentionPolicy
    -0.57
     nahilalakip
    -0.56
    脚注の使い方
    -0.56
     getItemCount
    -0.55
     виправивши
    -0.55
    POSITIVE LOGITS
    дию
    0.53
     Norman
    0.50
    Norman
    0.50
     Pays
    0.48
    Jîn
    0.44
     outputStream
    0.44
     Iro
    0.43
     бре
    0.42
    chine
    0.42
     Agg
    0.41
    Act Density 0.001%

    No Known Activations