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

    Neuronpedia

    INDEX
    Explanations

    tray

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.56
    c
    1.45
    is
    1.41
    1
    1.32
    a
    1.20
    (
    1.16
    of
    1.14
    5
    1.14
    are
    1.13
    the
    1.11
    POSITIVE LOGITS
     nobles
    0.95
     tray
    0.94
     роди
    0.94
     ც
    0.93
     модель
    0.92
     trays
    0.92
     времена
    0.92
     bandeja
    0.92
     विधायकों
    0.91
     Дон
    0.91
    Act Density 0.006%

    No Known Activations