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

    Neuronpedia

    INDEX
    Explanations

    dates (years, centuries, BC)

    oai_token-act-pair · gemini-2.0-flash

    dealing with time periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.01
     Efq
    -0.91
     BoxDecoration
    -0.90
    ConstraintMaker
    -0.90
    GEBURTSDATUM
    -0.84
    protoc
    -0.82
    contentLoaded
    -0.81
     &___
    -0.81
     ddelweddau
    -0.80
     tartalomajánló
    -0.79
    POSITIVE LOGITS
    <bos>
    0.60
     
    0.54
     pass
    0.53
    emp
    0.50
     to
    0.49
     v
    0.48
    拉克
    0.48
    '
    0.47
     n
    0.46
    pass
    0.46
    Act Density 1.920%

    No Known Activations