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

    Neuronpedia

    INDEX
    Explanations

    highlight show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wahl
    -0.09
     wählen
    -0.08
    -par
    -0.08
    279
    -0.08
    नेक
    -0.07
    淡
    -0.07
    પર
    -0.07
    പ്പെട്ടു
    -0.07
    **/↵
    -0.07
    ‍ഡ
    -0.07
    POSITIVE LOGITS
     benefits
    0.09
     доказ
    0.09
     superiority
    0.08
     выг
    0.08
    Benefits
    0.08
     favorable
    0.08
     ROI
    0.08
     مثلا
    0.08
    Testimonials
    0.08
     convinced
    0.08
    Act Density 0.073%

    No Known Activations