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

    Neuronpedia

    INDEX
    Explanations

    copying and pasting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மணியே
    0.46
     எண்ணெய்
    0.45
    icoter
    0.44
    নির্দিষ্ট
    0.43
    𒃻
    0.43
    ഹ്ലാദ
    0.43
    >.
    0.42
    깻
    0.41
    रिमेंट
    0.41
     கெல்வின்
    0.40
    POSITIVE LOGITS
     (
    0.83
    とその
    0.78
    (
    0.73
     và
    0.71
     wife
    0.70
     و
    0.66
     married
    0.66
     और
    0.65
     και
    0.64
    และ
    0.62
    Act Density 0.001%

    No Known Activations