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

    Neuronpedia

    INDEX
    Explanations

    sort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Giám
    -0.07
     Méd
    -0.07
     즐
    -0.06
     ребен
    -0.06
     Jab
    -0.06
     زی
    -0.06
     facilities
    -0.06
     Dinner
    -0.06
     Inner
    -0.06
     chú
    -0.06
    POSITIVE LOGITS
    .ACCESS
    0.06
    though
    0.06
     توسعه
    0.06
    Nor
    0.06
    -aff
    0.06
     sortOrder
    0.06
     repaint
    0.06
     کنم
    0.06
    .warn
    0.06
    .ir
    0.06
    Act Density 0.006%

    No Known Activations