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

    Neuronpedia

    INDEX
    Explanations

    iterating with for loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑖
    0.48
    菒
    0.42
    捭
    0.41
    IVES
    0.40
    )【
    0.39
     Knitting
    0.39
    ি
    0.39
     მისი
    0.39
    ലോ
    0.39
    ಜ
    0.37
    POSITIVE LOGITS
     _,
    0.91
     (_,
    0.67
    _,
    0.62
    (_,
    0.60
     item
    0.59
     each
    0.48
     filename
    0.45
     isinstance
    0.44
    item
    0.43
     bpy
    0.42
    Act Density 0.021%

    No Known Activations