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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noDo
    -0.54
     Vikipedi
    -0.50
    hatic
    -0.49
    Sucesor
    -0.49
    DoubleQuotes
    -0.49
    Full
    -0.48
    Forward
    -0.45
    wark
    -0.45
     brak
    -0.45
     Вікіпе
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.83
    andExpect
    0.62
     ExecuteAsync
    0.61
     GenerationType
    0.61
     Riproduzione
    0.60
    indd
    0.58
     فريبيس
    0.56
    uxxxx
    0.56
    Према
    0.53
     the
    0.52
    Act Density 0.003%

    No Known Activations