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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Construction
    -0.07
    录
    -0.07
     visitors
    -0.06
    功
    -0.06
    ανα
    -0.06
    682
    -0.06
     chiếc
    -0.06
     visitor
    -0.06
     جه
    -0.06
    citation
    -0.06
    POSITIVE LOGITS
    elleicht
    0.07
     cq
    0.07
    employer
    0.07
     )[
    0.07
    nts
    0.07
    地球
    0.06
    ROUGH
    0.06
    แสง
    0.06
    filesystem
    0.06
    (done
    0.06
    Act Density 0.018%

    No Known Activations