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

    Neuronpedia

    INDEX
    Explanations

    If... this, you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    1.24
    ري
    1.13
    ש
    1.12
    ز
    1.05
    ס
    1.02
    জ
    0.98
    ج
    0.95
    ро
    0.94
    l
    0.93
    वळ
    0.92
    POSITIVE LOGITS
    ิน
    1.14
     चाहें
    1.13
    तला
    1.06
    ਕਰ
    1.05
    že
    1.00
    ுள்ளது
    0.98
     واذا
    0.94
    再加上
    0.93
    tit
    0.88
     terjadi
    0.88
    Act Density 0.481%

    No Known Activations