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

    Neuronpedia

    INDEX
    Explanations

    sticker, наклейка

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bowel
    -0.09
    kunft
    -0.09
    عدة
    -0.08
    ieß
    -0.08
     baign
    -0.08
     innings
    -0.08
     sept
    -0.07
     erectile
    -0.07
     ebb
    -0.07
     clair
    -0.07
    POSITIVE LOGITS
     stickers
    0.13
     sticker
    0.11
    貼
    0.09
     Sticker
    0.09
     onto
    0.08
    patch
    0.08
     붙
    0.08
     badges
    0.08
    Sticker
    0.08
    贴
    0.08
    Act Density 0.012%

    No Known Activations