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

    Neuronpedia

    INDEX
    Explanations

    什么

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Asians
    -0.07
    hpp
    -0.07
    ón
    -0.07
    Cre
    -0.07
    -la
    -0.06
    ète
    -0.06
    roles
    -0.06
    _goto
    -0.06
    The
    -0.06
     Active
    -0.06
    POSITIVE LOGITS
    有什么
    0.08
     усе
    0.07
    λογία
    0.07
     wardrobe
    0.06
    ุตสาห
    0.06
     브
    0.06
     Serious
    0.06
    provide
    0.06
     виготов
    0.06
     दब
    0.06
    Act Density 0.003%

    No Known Activations