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

    Neuronpedia

    INDEX
    Explanations

    instances of excessive or abnormal levels in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    excessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.65
    tagHelperRunner
    -0.59
    providedIn
    -0.59
     initComponents
    -0.56
    léans
    -0.54
    arakhand
    -0.53
    exitRule
    -0.52
    JoinTable
    -0.52
    landing
    -0.51
    SqlDataReader
    -0.51
    POSITIVE LOGITS
     excessive
    1.74
    Excessive
    1.65
     Excessive
    1.62
    cessive
    1.44
     excessively
    1.33
     exces
    1.12
     berlebihan
    0.90
    过度
    0.81
     excesso
    0.78
     exceso
    0.77
    Act Density 0.011%

    No Known Activations