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

    Neuronpedia

    INDEX
    Explanations

    early stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     productividad
    0.86
     gestalten
    0.85
     performans
    0.81
     makes
    0.79
     момент
    0.78
     kinetic
    0.78
     grunn
    0.78
     만들기
    0.77
     product
    0.77
     transformations
    0.76
    POSITIVE LOGITS
    uge
    0.80
     Soap
    0.79
     Hội
    0.79
     أعلام
    0.77
    )।
    0.77
     vadanti
    0.77
    Cy
    0.76
    炉
    0.74
    CNN
    0.73
     służ
    0.73
    Act Density 0.006%

    No Known Activations