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

    Neuronpedia

    INDEX
    Explanations

    long periods of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আবার
    0.78
    peri
    0.78
    cute
    0.72
     ചില
    0.69
    一下
    0.68
    ivid
    0.68
    তিকর
    0.67
    শিষ্ট
    0.67
     ако
    0.66
    pham
    0.66
    POSITIVE LOGITS
     decades
    3.03
     years
    2.91
     longstanding
    2.72
     centuries
    2.58
    多年
    2.49
    多年的
    2.48
     longtime
    2.44
     long
    2.43
    years
    2.39
     वर्षों
    2.34
    Act Density 0.488%

    No Known Activations