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

    Neuronpedia

    INDEX
    Explanations

    surface and edges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தலைமை
    0.75
     Bend
    0.74
     केंद
    0.72
    రెడ్డి
    0.69
    储备
    0.67
     Bender
    0.67
    👯
    0.66
     System
    0.64
    शाही
    0.62
     설립
    0.62
    POSITIVE LOGITS
     surfaces
    3.09
     surface
    2.81
     Surfaces
    2.66
    surface
    2.45
     поверхность
    2.42
     поверхности
    2.41
    Surface
    2.38
     Surface
    2.35
     superficie
    2.31
     superfície
    2.30
    Act Density 0.479%

    No Known Activations