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

    Neuronpedia

    INDEX
    Explanations

    , and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.68
     of
    0.61
    in
    0.60
    is
    0.58
    (
    0.53
    of
    0.52
    en
    0.48
    n
    0.46
    r
    0.46
    ana
    0.46
    POSITIVE LOGITS
    ے
    0.57
    す
    0.50
    ും
    0.47
     milioane
    0.47
    他的
    0.47
    пи
    0.47
    စိတ်
    0.46
     нього
    0.46
     écailles
    0.46
     වීම
    0.46
    Act Density 4.484%

    No Known Activations