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

    Neuronpedia

    INDEX
    Explanations

    addressing you or someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你们
    2.39
    你們
    2.31
     jullie
    2.09
     আপনাদের
    2.08
     আপনারা
    2.05
     vocês
    2.03
     kalian
    1.98
     yourselves
    1.90
     ustedes
    1.85
     Vocês
    1.84
    POSITIVE LOGITS
     तुझ्या
    0.88
     உன்
    0.77
     तुझे
    0.70
     тво
    0.66
    তোমার
    0.60
     তোমার
    0.60
     तेरे
    0.57
     তোর
    0.56
     तुला
    0.55
     तुझ
    0.55
    Act Density 0.005%

    No Known Activations