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

    Neuronpedia

    INDEX
    Explanations

    Crawled, Kraken, CrawlSpider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Round
    0.44
     Round
    0.43
     rounding
    0.40
     sucesivamente
    0.38
     rounded
    0.38
    round
    0.38
     राउंड
    0.38
     round
    0.37
    really
    0.37
    blos
    0.37
    POSITIVE LOGITS
     kra
    0.45
    ㄥ
    0.40
     Partizan
    0.39
    粔
    0.39
     रवि
    0.38
     MER
    0.38
    糹
    0.38
     dů
    0.38
     подпис
    0.37
     डिजाइनर
    0.37
    Act Density 0.006%

    No Known Activations