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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Wirkung
    0.49
    birthday
    0.47
     बर्थडे
    0.47
     Birthday
    0.45
     persona
    0.44
     worden
    0.44
     widening
    0.44
     bandwidth
    0.42
    你会
    0.42
    ARR
    0.41
    POSITIVE LOGITS
    ujú
    0.50
     مباشر
    0.48
    沙
    0.46
     दरम्यान
    0.45
    ésre
    0.43
    州市
    0.43
    мян
    0.42
     enzym
    0.42
    ตั้ง
    0.42
     trục
    0.42
    Act Density 0.008%

    No Known Activations