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

    Neuronpedia

    INDEX
    Explanations

    später later později později

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    णू
    0.74
     فإن
    0.71
    డి
    0.70
     thì
    0.67
    则
    0.67
    ந்துள்ளது
    0.66
    прежнему
    0.65
    ຢ່າງ
    0.64
    眉
    0.64
    ऐसे
    0.64
    POSITIVE LOGITS
     later
    5.35
     Later
    4.67
    Later
    4.63
    later
    4.52
     später
    4.41
     senere
    4.09
     kasnije
    4.00
     позже
    3.95
     později
    3.86
     späteren
    3.86
    Act Density 0.471%

    No Known Activations