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

    Neuronpedia

    INDEX
    Explanations

    often but is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اپنے
    0.40
     Når
    0.40
    ಿನಿ
    0.38
     זי
    0.37
     birthdays
    0.37
    ສົ່ງ
    0.37
     특정
    0.37
    ጆች
    0.36
     coches
    0.35
     ຂ
    0.35
    POSITIVE LOGITS
     probablemente
    0.44
     მაგრამ
    0.44
    そらく
    0.43
     probabilmente
    0.42
     substantial
    0.41
    꽤
    0.41
     многи
    0.41
    有很多
    0.40
     imagination
    0.40
    有可能
    0.40
    Act Density 0.018%

    No Known Activations