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

    Neuronpedia

    INDEX
    Explanations

    references to statistical significance and related testing concepts

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

    statistical significance level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MethodManager
    -0.51
     pods
    -0.50
     createState
    -0.49
     trove
    -0.49
     ExecuteAsync
    -0.48
    ugeot
    -0.47
     BorderSide
    -0.47
    chiali
    -0.46
    ніципалі
    -0.46
     للمعارف
    -0.46
    POSITIVE LOGITS
     ceremonia
    0.41
     cuarent
    0.37
     estándar
    0.35
     condena
    0.34
    ásra
    0.34
     caza
    0.34
    IVEREF
    0.34
    SpringRunner
    0.34
     zákaz
    0.34
     marrón
    0.34
    Act Density 0.060%

    No Known Activations