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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and methodologies

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

    Statistical tests or comparisons

    np_acts-logits-general · gemini-2.0-flash

    statistical analysis of group differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.65
     myſelf
    -0.60
     defaultstate
    -0.59
     للمعارف
    -0.59
    Diwedd
    -0.57
     faſt
    -0.56
     MainAxisSize
    -0.55
    ThroughAttribute
    -0.55
    RegistryLite
    -0.54
     Houſe
    -0.52
    POSITIVE LOGITS
     distribution
    0.47
     Distribution
    0.43
     group
    0.40
     DISTRIBUTION
    0.39
    printStats
    0.38
    UnusedPrivate
    0.38
    ponses
    0.38
     distributions
    0.37
     للتو
    0.36
     StatefulWidget
    0.35
    Act Density 2.204%

    No Known Activations