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

    Neuronpedia

    INDEX
    Explanations

    after the definite article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இவ்வாறு
    0.43
     parejas
    0.43
    odos
    0.40
    will
    0.40
    existe
    0.40
    automat
    0.39
    Thus
    0.39
     এইরূপে
    0.39
    utilized
    0.39
    работа
    0.38
    POSITIVE LOGITS
     khẩu
    0.41
     quả
    0.41
     natal
    0.39
     trem
    0.38
     결
    0.37
     vaginalis
    0.37
     kết
    0.37
    也没有
    0.37
     tram
    0.36
     QC
    0.36
    Act Density 0.001%

    No Known Activations