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

    Neuronpedia

    INDEX
    Explanations

    legal settlements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attentive
    0.44
    र्स
    0.42
     Sequential
    0.42
    ণ্ঠে
    0.42
    adeep
    0.41
    in
    0.41
     Solutions
    0.41
     ভৌ
    0.41
     Runs
    0.41
     प्रदर्शन
    0.40
    POSITIVE LOGITS
    ੁਰ
    0.47
     алуу
    0.45
    只是
    0.45
    尽管
    0.45
     جبکہ
    0.45
     فوټبال
    0.44
    યા
    0.43
     পূর্ববাংলা
    0.43
    ING
    0.43
    VARI
    0.43
    Act Density 0.062%

    No Known Activations