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

    Neuronpedia

    INDEX
    Explanations

    180

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     literacy
    -0.10
     letter
    -0.08
     gedurende
    -0.08
    letter
    -0.08
    (column
    -0.08
    асында
    -0.08
    LETTER
    -0.07
     Cecilia
    -0.07
     peer
    -0.07
    (rows
    -0.07
    POSITIVE LOGITS
     protr
    0.09
     welded
    0.08
    Polygon
    0.08
     polygon
    0.08
    .Dock
    0.08
     fractured
    0.08
     कैम
    0.08
     खुले
    0.07
     polygons
    0.07
     معد
    0.07
    Act Density 0.007%

    No Known Activations