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

    Neuronpedia

    INDEX
    Explanations

    sun, kindness, stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bookstore
    0.43
     govor
    0.42
     किताबें
    0.41
    Herd
    0.41
     पुस्तकें
    0.40
    बोल
    0.39
    뉩
    0.39
     amplia
    0.38
     bağı
    0.38
    听说
    0.38
    POSITIVE LOGITS
     besten
    0.45
     वेस्ट
    0.43
     acetate
    0.42
     fastening
    0.42
     тест
    0.41
    絶対
    0.41
     Eurasian
    0.40
     কালে
    0.40
    わせて
    0.40
     faster
    0.39
    Act Density 0.082%

    No Known Activations