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

    Neuronpedia

    INDEX
    Explanations

    Storage instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    最大
    -0.09
    体现
    -0.09
    PCI
    -0.08
     تحول
    -0.08
    利益
    -0.08
    为何
    -0.08
     plaus
    -0.08
     matter
    -0.08
    当前
    -0.07
     convergence
    -0.07
    POSITIVE LOGITS
     출시
    0.08
     hugs
    0.08
     즐
    0.08
     chơi
    0.08
     제작
    0.08
     chopped
    0.08
     thưởng
    0.08
     defects
    0.08
    ادرات
    0.08
     사랑
    0.08
    Act Density 0.014%

    No Known Activations