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

    Neuronpedia

    INDEX
    Explanations

    phrase or clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     데이터
    0.47
     resultados
    0.46
     प्रगति
    0.46
    uyama
    0.45
     भागीदारों
    0.45
     جعفر
    0.44
     ferment
    0.43
     은행
    0.43
    idunt
    0.42
     宋
    0.42
    POSITIVE LOGITS
    По
    0.49
    त्र
    0.48
    tel
    0.46
    作为
    0.45
    प
    0.43
    ল্প
    0.42
     crown
    0.42
    лены
    0.42
    Кон
    0.42
    佲
    0.41
    Act Density 0.003%

    No Known Activations