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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific measurements or variables

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

    extreme variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.66
    IUrlHelper
    -0.61
    şört
    -0.54
     ویکی‌پدیا
    -0.53
    Personensuche
    -0.52
    Datuak
    -0.50
     محفوظة
    -0.48
    Билгалдахарш
    -0.48
    DeleteBehavior
    -0.48
    évaluateur
    -0.48
    POSITIVE LOGITS
     extremo
    0.43
    anmoins
    0.40
     keseluruhan
    0.40
     extreme
    0.40
    imanapun
    0.40
     variaciones
    0.39
     StatelessWidget
    0.38
     meliputi
    0.38
     extremos
    0.38
    atguigu
    0.37
    Act Density 0.253%

    No Known Activations