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

    Neuronpedia

    INDEX
    Explanations

    wall and its surroundings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inox
    0.77
    烬
    0.71
    uxi
    0.70
    TypeScript
    0.65
     TypeScript
    0.63
     маши
    0.63
    quale
    0.63
     tiện
    0.63
    executor
    0.63
    藕
    0.62
    POSITIVE LOGITS
     wall
    2.09
     Wall
    2.06
     walls
    2.05
    Wall
    1.97
     Walls
    1.89
     WALL
    1.80
    Walls
    1.73
    墙
    1.73
    wall
    1.71
    壁
    1.70
    Act Density 0.178%

    No Known Activations