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

    Neuronpedia

    INDEX
    Explanations

    winter and overwinter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জুলাই
    0.43
     дня
    0.42
     July
    0.39
     நீதிமன்ற
    0.38
     जुलाई
    0.36
     오전
    0.36
    ورية
    0.35
    鉐
    0.35
     nắng
    0.35
     JULY
    0.35
    POSITIVE LOGITS
     winter
    1.48
     overw
    1.36
    Winter
    1.34
    winter
    1.30
     Winter
    1.21
     зимо
    1.18
     vinter
    1.18
     WINTER
    1.17
    冬
    1.14
     hiver
    1.12
    Act Density 0.019%

    No Known Activations