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

    Neuronpedia

    INDEX
    Explanations

    confined to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ál
    0.50
    鏻
    0.49
    尽快
    0.49
     ऑस्ट्रेलियाई
    0.47
     Kanada
    0.45
     تكبرها
    0.43
    结婚
    0.43
    untuk
    0.43
    für
    0.43
    larım
    0.43
    POSITIVE LOGITS
     institutions
    0.47
     grained
    0.40
     syllabus
    0.39
     textures
    0.39
     caged
    0.39
     різних
    0.38
    Type
    0.38
     variously
    0.38
     concentric
    0.37
     المؤس
    0.37
    Act Density 0.027%

    No Known Activations