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

    Neuronpedia

    INDEX
    Explanations

    ladder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoeft
    -0.63
    AntiForgeryToken
    -0.59
    owulf
    -0.57
    SerializedName
    -0.56
     säkert
    -0.56
    PreExecute
    -0.55
    EndInit
    -0.54
     behöver
    -0.54
     necesarias
    -0.54
    pidou
    -0.54
    POSITIVE LOGITS
    出版年
    0.68
     uLocal
    0.57
     Wikispecies
    0.57
    PhysRevD
    0.54
    AsUp
    0.52
    Produzione
    0.52
     xoay
    0.47
     Roskov
    0.47
    faden
    0.47
    Carriera
    0.47
    Act Density 0.007%

    No Known Activations