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

    Neuronpedia

    INDEX
    Explanations

    ys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ing
    -0.08
    前三季度
    -0.08
     따라
    -0.07
     الا
    -0.07
    ⧽
    -0.07
    FORE
    -0.07
    蛱
    -0.07
    藁
    -0.07
    家装
    -0.07
    ingga
    -0.07
    POSITIVE LOGITS
    Squared
    0.07
     сложно
    0.07
    孕育
    0.07
     preserving
    0.06
     oko
    0.06
    极
    0.06
    씹
    0.06
    useppe
    0.06
     unimagin
    0.06
    天国继续
    0.06
    Act Density 0.311%

    No Known Activations