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

    Neuronpedia

    INDEX
    Explanations

    bibliographic references and citation formats

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

    References, citations, or bibliography entries

    np_acts-logits-general · gemini-2.0-flash

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sha
    -0.44
     dem
    -0.43
     Dem
    -0.41
    dem
    -0.41
    hot
    -0.41
    ha
    -0.39
    ary
    -0.38
    sed
    -0.38
     Chi
    -0.38
     weak
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.68
    期刊论文
    0.67
     Paglinawan
    0.66
    astéroïdes
    0.65
     oprot
    0.63
     EconPapers
    0.63
     الحره
    0.61
     مرئيه
    0.60
     arşivlendi
    0.60
    writeFieldEnd
    0.60
    Act Density 0.109%

    No Known Activations