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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs followed by you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adalah
    0.87
    Although
    0.76
     دارید
    0.70
    いは
    0.69
    いています
    0.69
    ικά
    0.67
    Par
    0.66
    是一個
    0.66
     ليس
    0.66
    주의
    0.65
    POSITIVE LOGITS
     they
    2.59
     we
    2.20
     они
    2.19
     you
    1.96
     вони
    1.96
     he
    1.76
    they
    1.71
     it
    1.70
     she
    1.70
    他们
    1.68
    Act Density 0.263%

    No Known Activations