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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to numerical values and quantities in various contexts

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

    multi-word tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTCX
    -0.43
     CITED
    -0.41
     INVENTION
    -0.41
    __*/
    -0.40
    IContainer
    -0.39
    くれました
    -0.39
     READING
    -0.39
    Merkmale
    -0.39
    CWE
    -0.39
    庁
    -0.38
    POSITIVE LOGITS
    richTextPanel
    0.47
     المعيارى
    0.46
     للمعارف
    0.43
     aDecoder
    0.41
    verifyException
    0.39
    adaptiveStyles
    0.37
     informée
    0.36
     Eſ
    0.36
     RoutedEventArgs
    0.34
     corresponding
    0.33
    Act Density 0.180%

    No Known Activations