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

    Neuronpedia

    INDEX
    Explanations

    listing items with asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     svjets
    0.41
     Lietuvos
    0.40
     waardoor
    0.39
    Subsequently
    0.38
    なのです
    0.37
     لیکن
    0.37
    但是我
    0.36
    डी
    0.36
     কিন্তু
    0.36
    stven
    0.36
    POSITIVE LOGITS
    에서는
    0.75
    では
    0.62
    場合は
    0.57
    の場合
    0.55
    에서의
    0.54
     では
    0.52
     경우는
    0.52
     ক্ষেত্রে
    0.51
     وہاں
    0.51
     where
    0.50
    Act Density 0.015%

    No Known Activations