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

    Neuronpedia

    INDEX
    Explanations

    technology or names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.86
    GEBURTSDATUM
    -0.76
    Datuak
    -0.74
    IndentedString
    -0.74
     joaat
    -0.72
    Personensuche
    -0.71
    ScopeManager
    -0.69
     kaarangay
    -0.69
     jadx
    -0.69
    UserScript
    -0.68
    POSITIVE LOGITS
     Western
    0.47
     western
    0.47
    awtextra
    0.45
    Western
    0.45
    r
    0.43
     r
    0.42
     vertre
    0.41
     trans
    0.41
    dür
    0.41
    ız
    0.39
    Act Density 0.000%

    No Known Activations