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

    Neuronpedia

    INDEX
    Explanations

    functional safety concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    越来越多
    0.59
     বাড়ছে
    0.52
    越来越
    0.51
    帮助
    0.50
    越来越多的
    0.50
     আপনার
    0.48
    很重要
    0.48
     বেড়েছে
    0.48
     તમારા
    0.47
     તમારી
    0.47
    POSITIVE LOGITS
     was
    0.52
    ང
    0.49
    iennes
    0.46
    기를
    0.45
    Commissioner
    0.44
    anjutkan
    0.44
     itinéraires
    0.43
     hereby
    0.43
     five
    0.42
    সিডেন্ট
    0.42
    Act Density 0.001%

    No Known Activations