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

    Neuronpedia

    INDEX
    Explanations

    Numbers and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    正是因为
    -0.07
    _PIPELINE
    -0.07
    下一篇
    -0.07
     fi
    -0.07
    ContentType
    -0.07
     đàn
    -0.07
    -breaking
    -0.07
     Nhân
    -0.06
    📄
    -0.06
     Encore
    -0.06
    POSITIVE LOGITS
    访问
    0.07
    把你
    0.07
    olics
    0.06
    触动
    0.06
    /window
    0.06
    跱
    0.06
    Hopefully
    0.06
     Ideally
    0.06
    ACTION
    0.06
    巴菲
    0.06
    Act Density 0.020%

    No Known Activations