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

    Neuronpedia

    INDEX
    Explanations

    determiner followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বা
    0.41
     all
    0.39
     các
    0.36
     những
    0.36
     Navidad
    0.36
    covariant
    0.36
    ѐ
    0.36
     হাজার
    0.36
     svih
    0.36
    seven
    0.35
    POSITIVE LOGITS
     দলটি
    0.47
    ？」
    0.36
    찌
    0.36
    ਲਾ
    0.36
    THON
    0.35
     సంస్థ
    0.35
    氏は
    0.34
    MathML
    0.34
    ими
    0.34
    氏
    0.34
    Act Density 0.086%

    No Known Activations