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

    Neuronpedia

    INDEX
    Explanations

    math questions (chinese)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ши
    -0.09
    rachen
    -0.09
     ransom
    -0.08
    uerpo
    -0.08
    _weather
    -0.08
     muuq
    -0.08
     развитие
    -0.08
     huéspedes
    -0.08
    870
    -0.08
     формирования
    -0.08
    POSITIVE LOGITS
    答案
    0.08
    Decimal
    0.08
    decimal
    0.07
    答
    0.07
     �
    0.07
    集中
    0.07
    ்ரீ
    0.07
     understated
    0.07
    answers
    0.07
     பெ
    0.07
    Act Density 0.009%

    No Known Activations