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

    Neuronpedia

    INDEX
    Explanations

    saying how much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ט
    0.61
    ية
    0.55
    ات
    0.53
    н
    0.51
    ئ
    0.50
    لي
    0.49
    وم
    0.48
    ن
    0.48
    л
    0.48
    רו
    0.47
    POSITIVE LOGITS
     제조
    0.51
     Велико
    0.51
     क्रॉप
    0.51
     вне
    0.48
     индекс
    0.48
     приме
    0.47
    দেশিক
    0.46
     कौन
    0.46
     communications
    0.46
     группы
    0.46
    Act Density 0.000%

    No Known Activations