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

    Neuronpedia

    INDEX
    Explanations

    instructions and questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۈ
    -0.09
    曼
    -0.07
    蹿
    -0.07
    培
    -0.07
    終
    -0.07
     يقوم
    -0.07
    落在
    -0.07
    kü
    -0.07
    Xd
    -0.07
    mann
    -0.07
    POSITIVE LOGITS
     authoritative
    0.08
    废话
    0.08
     $.
    0.07
    .rel
    0.07
    之作
    0.07
     pBuffer
    0.07
    图文
    0.07
     ==============================================================
    0.07
    烔
    0.07
    _movie
    0.07
    Act Density 0.001%

    No Known Activations