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

    Neuronpedia

    INDEX
    Explanations

    plastered on wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ソロ
    0.79
     picnic
    0.79
     picnics
    0.74
     probate
    0.74
     куро
    0.73
    嬤
    0.72
     golf
    0.72
    キャンプ
    0.72
    祺
    0.71
     Golf
    0.69
    POSITIVE LOGITS
     wall
    3.02
     walls
    3.00
    Wall
    2.75
    walls
    2.66
    wall
    2.63
     WALL
    2.59
     Wall
    2.58
     dinding
    2.57
    墙
    2.56
     Walls
    2.54
    Act Density 0.303%

    No Known Activations