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

    Neuronpedia

    INDEX
    Explanations

    start or time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tikang
    -0.56
     générations
    -0.55
     Suivez
    -0.52
     Monfieur
    -0.51
     verm
    -0.50
     roulant
    -0.50
     biß
    -0.50
    */;
    -0.49
     demain
    -0.49
    koff
    -0.48
    POSITIVE LOGITS
     of
    0.92
     EconPapers
    0.69
     propOrder
    0.66
    AndEndTag
    0.65
    ósitos
    0.60
    BeginContext
    0.59
    MENAFN
    0.58
    yfik
    0.57
    økt
    0.57
    arashtra
    0.57
    Act Density 0.080%

    No Known Activations