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

    Neuronpedia

    INDEX
    Explanations

    technology, Sentiment, Space, Migration, hosting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.68
    s
    0.61
    in
    0.57
     from
    0.55
     in
    0.52
     -
    0.50
    ق
    0.49
     for
    0.48
    :
    0.47
    ع
    0.46
    POSITIVE LOGITS
    ᴛ
    0.61
    𝗷
    0.51
     উপন
    0.49
     carrinho
    0.49
    𝘣
    0.48
    they
    0.47
    writerow
    0.47
    駒
    0.46
    랬
    0.46
    เขียน
    0.46
    Act Density 0.003%

    No Known Activations