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

    Neuronpedia

    INDEX
    Explanations

    quoted string identifiers in a structured data format

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

    json structure fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.45
     >::
    -0.42
     arşivlendi
    -0.40
    )))),
    -0.40
    فایل‌لار
    -0.40
     Besøkt
    -0.39
    imageshack
    -0.38
     patrulla
    -0.37
    >>>>>>>
    -0.37
    )}</
    -0.37
    POSITIVE LOGITS
    {'
    0.75
    ({"
    0.73
    ({'
    0.69
    {\"
    0.67
    {"
    0.67
     {"
    0.66
     {'
    0.65
    ":{"
    0.64
    ={'
    0.63
     كومونز
    0.57
    Act Density 0.041%

    No Known Activations