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

    Neuronpedia

    INDEX
    Explanations

    compression

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rong
    -0.07
    수가
    -0.07
    笱
    -0.06
    楮
    -0.06
    /date
    -0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
    noinspection
    -0.06
    Subviews
    -0.06
     onView
    -0.06
    <bits
    -0.06
    POSITIVE LOGITS
    组委会
    0.07
     леч
    0.07
     infiltr
    0.07
    =get
    0.07
     kidn
    0.07
    站
    0.06
    不再
    0.06
    喜爱
    0.06
    ±
    0.06
    HORT
    0.06
    Act Density 0.011%

    No Known Activations