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

    Neuronpedia

    INDEX
    Explanations

    providing information and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    G
    0.52
    S
    0.50
     that
    0.48
     ९
    0.47
     ८
    0.47
    M
    0.47
    す
    0.47
     ४
    0.47
     ५
    0.46
    し
    0.45
    POSITIVE LOGITS
    城乡
    0.45
    రణ
    0.45
     grizz
    0.44
     conclusively
    0.41
    一颗
    0.40
     иных
    0.40
    unjuk
    0.39
     luxuries
    0.38
     newList
    0.38
    పథ
    0.38
    Act Density 0.001%

    No Known Activations