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

    Neuronpedia

    INDEX
    Explanations

    graphic rendering or drawing functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caul
    0.46
     farewell
    0.42
     Andhra
    0.42
     wrecked
    0.40
     Bur
    0.39
    JF
    0.39
     wre
    0.38
     casualty
    0.37
     wreak
    0.37
     kings
    0.37
    POSITIVE LOGITS
    draw
    0.68
    Draw
    0.68
     Draw
    0.62
    edges
    0.51
    DRAW
    0.50
     draw
    0.47
    Drawing
    0.46
     drawing
    0.45
     Drawing
    0.45
     drawSprites
    0.45
    Act Density 0.000%

    No Known Activations