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

    Neuronpedia

    INDEX
    Explanations

    python3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    plotly
    0.43
    푸
    0.42
    galo
    0.42
    proj
    0.42
     фонда
    0.41
     поки
    0.41
    diving
    0.41
     prok
    0.40
    pois
    0.40
    lemen
    0.40
    POSITIVE LOGITS
     else
    0.46
     py
    0.45
     his
    0.45
     onscreen
    0.42
     clinched
    0.38
     our
    0.38
     alligator
    0.38
     셀
    0.38
     track
    0.38
     চিন
    0.38
    Act Density 0.021%

    No Known Activations