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

    Neuronpedia

    INDEX
    Explanations

    pronouns (he, they, you)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bunun
    0.49
     ያለው
    0.47
    ோவின்
    0.47
     இருந்தால்
    0.46
    者的
    0.46
     những
    0.46
     नसल्या
    0.45
     இவரது
    0.45
     dieses
    0.45
     تكون
    0.45
    POSITIVE LOGITS
    佢
    1.01
     তারা
    0.89
     they
    0.88
     ಅವರು
    0.77
     you
    0.75
    उन्होंने
    0.73
     त्यांनी
    0.72
     он
    0.71
     They
    0.70
     họ
    0.70
    Act Density 0.205%

    No Known Activations