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

    Neuronpedia

    INDEX
    Explanations

    created by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unborn
    0.26
     实现
    0.25
    πάν
    0.24
    获取
    0.24
    趼
    0.24
    dropBtn
    0.23
     获取
    0.23
    过程
    0.23
    单个
    0.23
    📩
    0.23
    POSITIVE LOGITS
     the
    0.51
     The
    0.34
    the
    0.33
     a
    0.33
     an
    0.32
    The
    0.32
     another
    0.29
    0.29
     teh
    0.28
     la
    0.28
    Act Density 0.164%

    No Known Activations