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

    Neuronpedia

    INDEX
    Explanations

    the word "text" followed by words related to forms, fields, and areas

    oai_token-act-pair · gemini-2.0-flash

    text-related elements or formats

    np_token-act-pair-logits · gpt-4o-mini

    text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propOrder
    -0.71
     Roskov
    -0.71
    abstractmethod
    -0.62
    ImageContext
    -0.59
    ########.
    -0.56
    CrossRef
    -0.54
    ftagPool
    -0.54
    mybatisplus
    -0.54
    قایناقلار
    -0.53
     Geraadpleegd
    -0.52
    POSITIVE LOGITS
     Aha
    0.52
    fiore
    0.47
     informed
    0.47
     Deve
    0.45
     opérés
    0.44
    URLException
    0.43
    urized
    0.43
     المعيارى
    0.43
     informs
    0.42
    깥
    0.42
    Act Density 2.484%

    No Known Activations