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

    Neuronpedia

    INDEX
    Explanations

    references to popular products and brands

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

    Product or model names

    np_acts-logits-general · gemini-2.0-flash

    product model names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.73
     doInBackground
    -0.63
     Púb
    -0.59
     ویکی‌پدیا
    -0.58
     незавершена
    -0.58
    WriteBarrier
    -0.56
    uxxxx
    -0.56
    SourceChecksum
    -0.56
    UnusedPrivate
    -0.53
     архивлан
    -0.53
    POSITIVE LOGITS
     รุ่น
    0.62
     مدل
    0.59
     серии
    0.58
    ')")
    0.57
     serii
    0.55
    脚注
    0.54
     Majesty
    0.54
     Voyager
    0.52
    製の
    0.52
     modelo
    0.51
    Act Density 0.322%

    No Known Activations