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

    Neuronpedia

    INDEX
    Explanations

    dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.77
    er
    0.71
    -
    0.70
    ann
    0.66
     budding
    0.65
    and
    0.64
     항상
    0.64
     headlight
    0.62
    ಾರ
    0.61
     computation
    0.61
    POSITIVE LOGITS
    Опера
    0.93
    Се
    0.84
     têm
    0.83
    ق
    0.80
    IC
    0.80
    Спа
    0.78
    Πα
    0.78
    Ча
    0.77
    穸
    0.77
    ED
    0.76
    Act Density 0.300%

    No Known Activations