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

    Neuronpedia

    INDEX
    Explanations

    for this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Semua
    0.52
     모든
    0.48
     끊
    0.43
    の内
    0.42
     새로운
    0.41
     Quelles
    0.41
     외국
    0.41
     각종
    0.41
     மற்ற
    0.41
     표현
    0.40
    POSITIVE LOGITS
     aide
    0.40
    启动
    0.40
     concise
    0.39
    hel
    0.39
     feedings
    0.39
     infantry
    0.38
     fusible
    0.38
     senc
    0.38
     tube
    0.38
     palust
    0.38
    Act Density 0.003%

    No Known Activations