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

    Neuronpedia

    INDEX
    Explanations

    bes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gallon
    -0.08
    Commercial
    -0.07
     introdu
    -0.07
     variants
    -0.07
    lections
    -0.07
    gradient
    -0.07
     Sour
    -0.06
    gallery
    -0.06
    ायद
    -0.06
     دان
    -0.06
    POSITIVE LOGITS
    BTC
    0.07
    engineering
    0.07
     مشهد
    0.06
    .Sequential
    0.06
    -twitter
    0.06
     обязан
    0.06
     нас
    0.06
    ادگی
    0.06
    yleft
    0.06
     подроб
    0.06
    Act Density 0.015%

    No Known Activations