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

    Neuronpedia

    INDEX
    Explanations

    math questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    으면
    -0.08
    	wait
    -0.07
    .car
    -0.07
    окси
    -0.07
    Ошибка
    -0.07
     gn
    -0.06
     memorial
    -0.06
    мот
    -0.06
     catches
    -0.06
    -threat
    -0.06
    POSITIVE LOGITS
    기준
    0.07
     pooled
    0.06
     debtor
    0.06
     Celtics
    0.06
     formas
    0.06
     Kes
    0.06
    รษฐ
    0.06
    홈
    0.06
     Đảng
    0.06
    724
    0.06
    Act Density 0.002%

    No Known Activations