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

    Neuronpedia

    INDEX
    Explanations

    hello world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ніципа
    0.82
    רון
    0.71
    मेय
    0.68
    header
    0.67
    수가
    0.67
     ẹ
    0.66
    ojas
    0.65
    iejsc
    0.63
    ្នាំ
    0.63
    鋏
    0.63
    POSITIVE LOGITS
     world
    6.03
    world
    5.32
    世界
    5.03
     mundo
    4.82
    World
    4.57
     wereld
    4.54
     World
    4.51
     worlds
    4.49
     dunia
    4.42
     세계
    4.33
    Act Density 0.334%

    No Known Activations