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

    Neuronpedia

    INDEX
    Explanations

    houses, gardens, and game worlds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    スナー
    0.61
    ς
    0.59
    ڑے
    0.59
    ówno
    0.59
    atthe
    0.58
    zovaniyu
    0.57
    жду
    0.56
    щий
    0.56
    фан
    0.56
    στή
    0.56
    POSITIVE LOGITS
    g
    0.77
    o
    0.68
    p
    0.67
    k
    0.66
    z
    0.64
    n
    0.64
    le
    0.59
    b
    0.58
     We
    0.57
    te
    0.55
    Act Density 0.002%

    No Known Activations