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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    non-English or special characters

    np_token-act-pair-logits · gpt-4o-mini

    say number 8

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     StatefulWidget
    -0.58
     StatelessWidget
    -0.57
     cas
    -0.56
    runApp
    -0.54
    Kanpo
    -0.50
     Thor
    -0.47
    oso
    -0.47
     onView
    -0.47
     (!__
    -0.46
     Downs
    -0.46
    POSITIVE LOGITS
    הערות
    0.74
     חיצוניים
    0.70
     يتيمه
    0.69
    InjectAttribute
    0.68
    AddTagHelper
    0.68
     zelve
    0.66
     avoient
    0.64
    قایناقلار
    0.62
     متحده
    0.62
     GENERATED
    0.60
    Act Density 10.262%

    No Known Activations