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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DeepCopy
    -0.27
     kidding
    -0.26
    å¤įæĿĤçļĦ
    -0.26
    -China
    -0.26
    @student
    -0.25
    ionate
    -0.25
    odox
    -0.25
    误åĮº
    -0.25
    æģ°å¥½
    -0.24
    mlink
    -0.24
    POSITIVE LOGITS
    åıĤ
    0.28
    ↵↵
    0.28
    ä»İä¸ļ人åijĺ
    0.27
    æĭĽ
    0.27
     remarks
    0.26
     outgoing
    0.26
     remark
    0.26
    议论
    0.26
    .respond
    0.26
    è¿Ł
    0.26
    Act Density 0.056%

    No Known Activations