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

    Neuronpedia

    INDEX
    Explanations

    no single way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     присутствует
    0.42
     contém
    0.41
     mellem
    0.40
     присут
    0.38
    })$.
    0.38
     Гри
    0.38
    有什么
    0.37
    })}{\
    0.37
     abbia
    0.37
     tinham
    0.37
    POSITIVE LOGITS
    两种
    0.71
     ways
    0.70
    兩種
    0.59
     myriad
    0.55
     طرق
    0.55
     plenty
    0.54
     способов
    0.50
     maneiras
    0.50
     maneras
    0.50
     façons
    0.49
    Act Density 0.019%

    No Known Activations