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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estekak
    -0.72
     فريبيس
    -0.72
     invokingState
    -0.68
     ModelExpression
    -0.67
    SourceChecksum
    -0.66
     utafitiHapana
    -0.65
     समीक्षक
    -0.64
    ⓧ
    -0.62
    MessageOf
    -0.62
    OGND
    -0.62
    POSITIVE LOGITS
     faſt
    0.59
     purpoſe
    0.58
     simple
    0.57
     ſch
    0.56
     perſon
    0.54
     motivating
    0.54
     uſ
    0.53
     intuitive
    0.53
     MainAxisSize
    0.53
     ſmall
    0.52
    Act Density 0.003%

    No Known Activations