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

    Neuronpedia

    INDEX
    Explanations

    specific topics or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ／
    0.41
     unele
    0.40
    io
    0.38
    )_{
    0.38
     "¿
    0.38
    (@"
    0.38
    +"/
    0.36
     acht
    0.36
    ঙ্গা
    0.35
     athleticism
    0.35
    POSITIVE LOGITS
    尤其是
    0.59
    特别是
    0.58
     особенно
    0.55
     특히
    0.52
     terutama
    0.51
     khususnya
    0.49
    類の
    0.48
     especially
    0.47
    特に
    0.47
     Especially
    0.46
    Act Density 0.468%

    No Known Activations