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

    Neuronpedia

    INDEX
    Explanations

    multilingual explanations and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тексто
    0.47
    сса
    0.44
     те
    0.43
    РА
    0.42
     оптими
    0.42
    ный
    0.41
     раз
    0.41
     (
    0.41
     и
    0.40
    Раз
    0.40
    POSITIVE LOGITS
     모든
    0.59
     관련된
    0.58
     일반적으로
    0.55
     전에
    0.54
     필요한
    0.54
     inhomogeneities
    0.49
     위에
    0.48
     ಮನೆಯ
    0.48
     발생하는
    0.48
     앞에서
    0.47
    Act Density 0.009%

    No Known Activations