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

    Neuronpedia

    INDEX
    Explanations

    area and region

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vs
    0.70
    深深
    0.64
     vs
    0.62
     versus
    0.61
     infinit
    0.60
     forgetting
    0.59
    clerotic
    0.58
     slipper
    0.58
    versus
    0.57
    ترف
    0.56
    POSITIVE LOGITS
     area
    2.26
     region
    2.20
     local
    2.03
     المنطقة
    1.99
     região
    1.98
     Area
    1.90
    area
    1.89
    local
    1.85
     지역
    1.82
     región
    1.82
    Act Density 0.425%

    No Known Activations