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

    Neuronpedia

    INDEX
    Explanations

    calendar days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    2.49
    s
    2.39
    ים
    2.28
     insect
    2.06
    ات
    2.05
    sellers
    2.05
     bilayers
    2.03
    ‍♀
    2.02
    在
    2.01
    बिग
    1.98
    POSITIVE LOGITS
     рождения
    2.70
     واللي
    2.66
    break
    2.36
    dreams
    2.25
    मर्रा
    2.17
    𝗶
    2.08
    ेंद
    2.06
    ग्विजय
    2.05
     lucr
    2.05
    ्ञ
    2.02
    Act Density 0.216%

    No Known Activations