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

    Neuronpedia

    INDEX
    Explanations

    initializing arrays with shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sınır
    0.44
    骠
    0.42
     कीजिएगा
    0.41
     تړل
    0.41
    昦
    0.41
     kwietnia
    0.40
    𒀊
    0.39
    bourg
    0.39
     nacionales
    0.39
     ব্যয়
    0.39
    POSITIVE LOGITS
    shape
    0.74
     shape
    0.72
     $(
    0.70
     Shape
    0.66
     dims
    0.66
    =(
    0.64
    $(
    0.63
    Shape
    0.61
     dim
    0.60
     tuple
    0.60
    Act Density 0.011%

    No Known Activations