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

    Neuronpedia

    INDEX
    Explanations

    knowledge and specificity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     คุณ
    0.46
     कामयाबी
    0.40
    となり
    0.40
     defeat
    0.39
     adore
    0.38
     Bạn
    0.38
     You
    0.38
    this
    0.37
    because
    0.37
     transporte
    0.37
    POSITIVE LOGITS
     εκεί
    0.46
     règles
    0.42
     vulgaris
    0.42
     speculating
    0.41
     runways
    0.41
    getMeteringAreas
    0.40
     অভিহিত
    0.40
    Mock
    0.39
     пев
    0.39
    ［
    0.39
    Act Density 0.002%

    No Known Activations