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

    Neuronpedia

    INDEX
    Explanations

    what I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тях
    0.88
     وقلنا
    0.88
     hänen
    0.77
     nende
    0.72
     చేస్తున్నారు
    0.71
    ڇ
    0.69
    咩
    0.68
    ్రా
    0.68
     نفسك
    0.68
    ůli
    0.68
    POSITIVE LOGITS
     I
    5.72
    I
    4.51
     আমি
    3.79
     मैं
    3.47
    私は
    3.26
    我
    3.25
     tôi
    3.23
    আমি
    3.19
     我
    3.17
     நான்
    3.09
    Act Density 2.638%

    No Known Activations