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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and formatting in written text

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

    dates and numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.49
    UrlResolution
    -0.48
    yntaxException
    -0.45
    featureID
    -0.43
    ServletException
    -0.41
    رشف
    -0.38
    AccessorTable
    -0.38
    rieks
    -0.37
    ruptedException
    -0.36
    sizeCache
    -0.36
    POSITIVE LOGITS
    出版年
    0.63
     musical
    0.59
     cultural
    0.54
     culinary
    0.52
     linguistic
    0.52
    Mathematical
    0.51
     mathematical
    0.50
     molecular
    0.50
     Cultural
    0.50
     mental
    0.49
    Act Density 0.631%

    No Known Activations