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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.73
     whoſe
    -0.71
     unknownFields
    -0.70
     uſed
    -0.69
     ſp
    -0.68
    MigrationBuilder
    -0.68
     pleaſure
    -0.68
     ſta
    -0.68
     purpoſe
    -0.67
     raiſ
    -0.66
    POSITIVE LOGITS
    ArrowToggle
    0.68
     of
    0.61
     المعيارى
    0.47
    ment
    0.45
     IndexPath
    0.45
    msford
    0.45
    Portail
    0.43
     của
    0.42
     lenker
    0.40
     NSCoder
    0.40
    Act Density 0.133%

    No Known Activations