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

    Neuronpedia

    INDEX
    Explanations

    design and efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commencé
    0.43
     históricos
    0.43
     हिस्ट्री
    0.41
     continuando
    0.41
     phenomenology
    0.41
     Forming
    0.41
     prej
    0.40
     الاشت
    0.40
     começa
    0.40
     Geschichte
    0.40
    POSITIVE LOGITS
    Efficiency
    0.62
    效率
    0.61
    efficiency
    0.59
     efficiency
    0.58
    design
    0.55
    设计
    0.55
    efficient
    0.54
     Efficiency
    0.54
    Design
    0.53
     효율
    0.53
    Act Density 0.019%

    No Known Activations