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

    Neuronpedia

    INDEX
    Explanations

    legal, medical, judgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     යුතු
    0.46
     நாடு
    0.46
     ರೂ
    0.45
    ovaniyu
    0.45
     കൂടി
    0.44
    朹
    0.44
    apaccay
    0.44
    '`--
    0.44
    やや
    0.43
    rosis
    0.43
    POSITIVE LOGITS
    ؤال
    0.52
    ц
    0.49
     judgmental
    0.49
    ни
    0.46
    判
    0.46
     judgments
    0.46
    бі
    0.45
     belief
    0.45
     stances
    0.45
    sz
    0.45
    Act Density 0.003%

    No Known Activations