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

    Neuronpedia

    INDEX
    Explanations

    described

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跎
    -0.07
    .GetType
    -0.07
    容
    -0.07
    Geo
    -0.07
    stm
    -0.07
     <>
    -0.07
    енд
    -0.07
    吃饱
    -0.07
    adge
    -0.07
     bd
    -0.07
    POSITIVE LOGITS
    '));↵
    0.08
     две
    0.08
     السابع
    0.07
    ائ
    0.07
    ánh
    0.07
     الإلكترو
    0.07
    _avg
    0.07
    PERSON
    0.07
    nęła
    0.07
    价值观
    0.07
    Act Density 0.002%

    No Known Activations