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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    财政
    0.44
    上涨
    0.43
    的市场
    0.42
    举办
    0.40
    创意
    0.40
    公园
    0.40
    基础设施
    0.40
    秘书
    0.40
    ravés
    0.39
     회사
    0.39
    POSITIVE LOGITS
    P
    0.50
    Q
    0.45
     x
    0.45
    C
    0.44
    {\
    0.43
    0
    0.43
    V
    0.42
     P
    0.42
     C
    0.42
    N
    0.42
    Act Density 0.983%

    No Known Activations