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

    Neuronpedia

    INDEX
    Explanations

    ingredients and measurements in recipes

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

    Numbers or fractions written out in English

    np_acts-logits-general · gemini-2.0-flash

    numbers or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.74
     للمعارف
    -0.74
    RenderAtEndOf
    -0.72
    ItemBackground
    -0.70
    日閲覧
    -0.69
    ThemeOverlay
    -0.69
    +#+#
    -0.66
    sizeCache
    -0.66
    pecially
    -0.64
     חיצוניים
    -0.64
    POSITIVE LOGITS
     two
    1.14
    two
    0.90
     deux
    0.89
     
    0.84
     one
    0.84
     zwei
    0.78
     dvě
    0.77
     kaksi
    0.76
     dwie
    0.74
     three
    0.74
    Act Density 0.341%

    No Known Activations