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

    Neuronpedia

    INDEX
    Explanations

    since

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    到时候
    0.85
     nanti
    0.63
    下次
    0.61
     nantinya
    0.59
     করলে
    0.58
     থাকছে
    0.57
     nächsten
    0.56
     yapılacak
    0.54
     செய்தால்
    0.54
     മറ്റൊരു
    0.52
    POSITIVE LOGITS
     since
    5.06
    since
    4.50
     depuis
    4.25
     sejak
    4.25
     منذ
    4.22
    Since
    4.03
     seit
    4.00
     Since
    3.97
     desde
    3.89
     sinds
    3.58
    Act Density 0.391%

    No Known Activations