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

    Neuronpedia

    INDEX
    Explanations

    quotations and dialogue in text

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

    opening and closing quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diantaranya
    -0.46
    愷
    -0.42
    bleven
    -0.42
    新たに
    -0.41
     erfolgte
    -0.41
    ‌ی
    -0.38
    jstor
    -0.38
    újo
    -0.37
    épend
    -0.36
     aank
    -0.36
    POSITIVE LOGITS
     ویکی‌پدی
    0.54
    AddTagHelper
    0.53
    ſelf
    0.52
     resourceCulture
    0.47
    nvarchar
    0.46
     itſelf
    0.46
    ſelves
    0.46
     CallOverrides
    0.44
     SDLK
    0.43
     Verſ
    0.43
    Act Density 0.025%

    No Known Activations