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

    Neuronpedia

    INDEX
    Explanations

    width

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étage
    0.41
     heights
    0.41
     scrubs
    0.41
    Female
    0.40
     خانم
    0.40
     invers
    0.39
     हाइट
    0.38
     Female
    0.38
    Heights
    0.38
    setFixedHeight
    0.38
    POSITIVE LOGITS
     Width
    1.12
     width
    1.10
     ширина
    1.07
     шири
    1.06
    宽度
    1.05
     widths
    1.03
    Width
    1.02
     WIDTH
    1.01
    width
    1.00
    WIDTH
    0.97
    Act Density 0.262%

    No Known Activations