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

    Neuronpedia

    INDEX
    Explanations

    overlay=true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abhavam
    0.46
     গার্ডিয়ান
    0.41
    ንስ
    0.39
     регулярно
    0.39
    etition
    0.39
    arasi
    0.39
     उन्नति
    0.38
     सिस्टम
    0.38
     remit
    0.38
    褰
    0.38
    POSITIVE LOGITS
    مد
    0.49
    Не
    0.45
    مو
    0.43
    О
    0.43
    Ⲟ
    0.43
    ிக
    0.43
    包
    0.43
    इ
    0.40
    Во
    0.39
    Known
    0.39
    Act Density 0.000%

    No Known Activations