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

    Neuronpedia

    INDEX
    Explanations

    known for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あります
    0.43
     实现
    0.42
    DIFF
    0.39
    есть
    0.38
     سکے۔
    0.38
    ARN
    0.38
     Jul
    0.37
     রয়েছে
    0.37
     गोयल
    0.37
     JAMES
    0.37
    POSITIVE LOGITS
     sebagai
    0.68
     worldwide
    0.59
     internationally
    0.59
     ismert
    0.58
     dikenal
    0.57
    worldwide
    0.54
     bekend
    0.53
     known
    0.52
     bekannt
    0.52
     извест
    0.50
    Act Density 0.004%

    No Known Activations