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

    Neuronpedia

    INDEX
    Explanations

    strings and punctuation related to code syntax

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

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ly
    -0.63
    ness
    -0.53
    تفصیلات
    -0.53
     المعيارى
    -0.52
    出版年
    -0.51
    otide
    -0.49
    soever
    -0.46
    sweise
    -0.46
    __":
    -0.46
    ology
    -0.45
    POSITIVE LOGITS
    してみて
    0.45
    Saman
    0.42
    Parameteri
    0.42
    devo
    0.41
    tott
    0.41
    ്‍
    0.39
    wegen
    0.39
    quatre
    0.39
     Moun
    0.39
    Manbalar
    0.39
    Act Density 0.023%

    No Known Activations