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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addGroup
    -0.08
    小程序
    -0.08
    :expr
    -0.07
     selv
    -0.07
    这支
    -0.07
    搞好
    -0.07
    egas
    -0.07
     Ney
    -0.07
    ificance
    -0.07
    -send
    -0.07
    POSITIVE LOGITS
    重复
    0.06
    ل
    0.06
    勇敢
    0.06
    运
    0.06
    Privacy
    0.06
    し
    0.06
     compressed
    0.06
    postcode
    0.06
    对应的
    0.06
     diarrhea
    0.06
    Act Density 0.218%

    No Known Activations