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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and quotation marks in text

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

    letter sequences and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.70
    الدراسه
    -0.64
     stiefe
    -0.63
     trató
    -0.60
     fashiola
    -0.59
     ویکی‌پدی
    -0.58
     camiset
    -0.57
    agissait
    -0.57
     ſeinen
    -0.56
     entretenimiento
    -0.56
    POSITIVE LOGITS
    wapV
    0.40
     letter
    0.38
     arth
    0.38
     alphabet
    0.36
     alphabets
    0.36
     PyLong
    0.36
    NOPQRST
    0.36
     letters
    0.35
     orth
    0.34
     бук
    0.33
    Act Density 0.065%

    No Known Activations