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

    Neuronpedia

    INDEX
    Explanations

    temporal context, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     നിർ
    0.70
     custom
    0.68
     韓国
    0.67
     tùy
    0.67
     favorite
    0.65
     특징
    0.64
     kmeans
    0.63
     potenz
    0.62
    𝔪
    0.61
    itl
    0.61
    POSITIVE LOGITS
     tanggal
    1.38
     dated
    1.27
    วันที่
    1.27
    dated
    1.27
     بتاريخ
    1.17
     date
    1.16
     Dated
    1.15
    DATE
    1.13
     ngày
    1.11
     DATE
    1.09
    Act Density 0.049%

    No Known Activations