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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -1.03
     Roskov
    -1.02
    HtmlAttribute
    -0.89
     فريبيس
    -0.87
     propOrder
    -0.87
    Personendaten
    -0.86
    Referències
    -0.84
     Paglinawan
    -0.84
     cherchés
    -0.84
    afficheront
    -0.79
    POSITIVE LOGITS
    y
    0.63
    Y
    0.61
    ly
    0.57
    nt
    0.56
    E
    0.56
    ne
    0.54
    ro
    0.54
    yk
    0.54
    te
    0.53
    ys
    0.53
    Act Density 0.105%

    No Known Activations