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

    Neuronpedia

    INDEX
    Explanations

    Named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recognized
    -0.46
     فريبيس
    -0.45
     widely
    -0.43
    Famous
    -0.43
    有名な
    -0.43
     znám
    -0.41
     معروف
    -0.41
     prominent
    -0.40
     internationally
    -0.40
     popular
    -0.40
    POSITIVE LOGITS
     filmmakers
    0.73
     biologists
    0.71
     scientists
    0.69
     actresses
    0.69
     physicists
    0.68
     comedians
    0.68
    logists
    0.68
     researchers
    0.66
     nuns
    0.66
     Researchers
    0.65
    Act Density 0.004%

    No Known Activations