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

    Neuronpedia

    INDEX
    Explanations

    you all / folks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тебе
    0.87
     তোমাকে
    0.79
     तुझे
    0.79
     тво
    0.79
     तुझ्या
    0.79
     তোমার
    0.77
    তোমার
    0.77
     உன்
    0.76
     তুমি
    0.76
     тобі
    0.75
    POSITIVE LOGITS
    你们
    2.25
    你們
    2.25
     yourselves
    2.20
     আপনাদের
    2.09
     আপনারা
    2.09
     jullie
    2.06
     kalian
    1.99
     Vocês
    1.84
     vocês
    1.83
     كلكم
    1.65
    Act Density 0.023%

    No Known Activations