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

    Neuronpedia

    INDEX
    Explanations

    finding size in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     float
    0.42
     FLOAT
    0.40
    פור
    0.40
     पाव
    0.39
     cpp
    0.39
     Ken
    0.39
     Pens
    0.39
    asjon
    0.38
     Jon
    0.38
     Forgot
    0.38
    POSITIVE LOGITS
    size
    1.02
     size
    0.92
    unsigned
    0.74
     Size
    0.66
    Size
    0.64
    usize
    0.60
     SIZE
    0.60
    auto
    0.59
     usize
    0.57
     размер
    0.56
    Act Density 0.013%

    No Known Activations