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

    Neuronpedia

    INDEX
    Explanations

    years and decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.33
    কে
    0.31
    os
    0.30
    气息
    0.29
     পরিমাণ
    0.29
     snelheid
    0.29
     människ
    0.28
     स्वादिष्ट
    0.28
    น้ำ
    0.27
     দূরত্ব
    0.27
    POSITIVE LOGITS
    .
    0.34
    ineties
    0.30
    licher
    0.28
     industrialized
    0.28
     начало
    0.27
    ﾙ
    0.27
     sixties
    0.27
     eighties
    0.27
    쿡
    0.26
     ста
    0.26
    Act Density 0.047%

    No Known Activations