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

    Neuronpedia

    INDEX
    Explanations

    Ternary operator, list comprehension, proprietorships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سری
    0.44
    ieri
    0.43
    imleri
    0.43
     گذر
    0.43
     Origin
    0.42
     διο
    0.41
     earned
    0.41
    BA
    0.40
    ocyclic
    0.40
    主演
    0.39
    POSITIVE LOGITS
    չ
    0.58
    че
    0.50
    場所
    0.43
    кета
    0.43
     теат
    0.43
    いた
    0.43
     без
    0.43
    ор
    0.43
    profits
    0.42
     гля
    0.42
    Act Density 0.004%

    No Known Activations