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

    Neuronpedia

    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ara
    -0.07
    pur
    -0.07
     Marks
    -0.07
    watch
    -0.06
    erculosis
    -0.06
    ackers
    -0.06
     тем
    -0.06
     Talk
    -0.06
     Scheduled
    -0.06
     商
    -0.06
    POSITIVE LOGITS
    ،↵
    0.08
    :return
    0.07
    !(
    0.07
     이미지
    0.06
     hsv
    0.06
    »،
    0.06
    (sc
    0.06
    区域
    0.06
    ansı
    0.06
    ESC
    0.06
    Act Density 0.015%

    No Known Activations