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

    Neuronpedia

    INDEX
    Explanations

    test questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istr
    -0.08
    intree
    -0.08
    商家
    -0.08
    드립니다
    -0.07
    Whether
    -0.07
    댁
    -0.07
    STD
    -0.07
    锂电池
    -0.07
    rtc
    -0.07
     Validates
    -0.07
    POSITIVE LOGITS
    贡献
    0.07
     relations
    0.07
     thank
    0.07
    ans
    0.06
     Sau
    0.06
    'u
    0.06
     integrity
    0.06
     форма
    0.06
     consul
    0.06
    _MASK
    0.06
    Act Density 0.117%

    No Known Activations