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

    Neuronpedia

    INDEX
    Explanations

    numbers in sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.92
     only
    0.86
    3
    0.79
    1
    0.77
     Only
    0.69
    5
    0.68
    0
    0.67
    only
    0.67
     might
    0.66
    are
    0.66
    POSITIVE LOGITS
    ិច្
    0.95
    恴
    0.90
    及び
    0.89
     وأ
    0.87
    ﮄ
    0.86
    <unused1781>
    0.86
     ול
    0.85
     וש
    0.85
     宋
    0.85
    വും
    0.84
    Act Density 0.797%

    No Known Activations