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

    Neuronpedia

    INDEX
    Explanations

    their possessive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    your
    0.50
     ਤੁਹਾ
    0.49
     لوگوں
    0.48
     ඔබේ
    0.48
    大家的
    0.48
     kullanılır
    0.47
     আপনার
    0.47
     लोगों
    0.47
    人の
    0.47
     bagi
    0.46
    POSITIVE LOGITS
     their
    0.63
     leurs
    0.63
     ihres
    0.61
     themselves
    0.57
     loro
    0.56
    their
    0.55
    Their
    0.55
     তাঁদের
    0.55
     Their
    0.54
     ihrem
    0.52
    Act Density 0.016%

    No Known Activations