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

    Neuronpedia

    INDEX
    Explanations

    expressions related to freedom, choice, and confidentiality

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

    confidential and safe services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.46
     useParams
    -0.45
    ourite
    -0.43
     Num
    -0.43
    บ้าง
    -0.41
     Perubahan
    -0.41
     sometimes
    -0.41
     חיצוניים
    -0.40
     hơn
    -0.39
    чатки
    -0.39
    POSITIVE LOGITS
    contentLoaded
    0.66
    :✨
    0.48
    XtraReports
    0.44
     ویکی‌پدی
    0.44
    protetor
    0.40
    Rohy
    0.40
    Personensuche
    0.38
     Италијани
    0.38
     createSprite
    0.37
    encodeWith
    0.36
    Act Density 0.029%

    No Known Activations