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

    Neuronpedia

    INDEX
    Explanations

    sentence-ending punctuation marks

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

    periods and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.91
    parsedMessage
    -0.77
    yntaxException
    -0.74
    +#+#
    -0.69
    MLLoader
    -0.68
     betweenstory
    -0.68
     ExecuteAsync
    -0.66
    richTextPanel
    -0.65
    ſcher
    -0.65
     المعيارى
    -0.65
    POSITIVE LOGITS
    .,
    0.42
    _
    0.41
     Bewußt
    0.41
     daß
    0.39
     Einfluß
    0.37
     Miß
    0.37
     muß
    0.35
    0.35
     biß
    0.35
    -
    0.35
    Act Density 0.087%
    No Known Activations