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

    Neuronpedia

    INDEX
    Explanations

    months and future predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ድረስ
    0.45
     videojuegos
    0.43
     እስከ
    0.43
     hingga
    0.41
     zodat
    0.41
    വയ
    0.40
     úlo
    0.40
     자체가
    0.39
     waarbij
    0.39
    }=$
    0.38
    POSITIVE LOGITS
     will
    0.78
    will
    0.70
     будут
    0.64
     будет
    0.61
    我们会
    0.59
     sẽ
    0.59
    将会
    0.58
    我們會
    0.58
     станет
    0.57
     આવશે
    0.56
    Act Density 0.001%

    No Known Activations