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

    Neuronpedia

    INDEX
    Explanations

    Republic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    습니다
    2.28
    ları
    1.81
    न्द्र
    1.81
    して
    1.76
     dựng
    1.75
     inconclusive
    1.71
    ୍
    1.69
    اں
    1.66
    pOt
    1.63
     있으며
    1.58
    POSITIVE LOGITS
    t
    2.95
    ه
    2.48
    iD
    2.36
    하신
    2.31
    م
    2.28
    Ад
    2.27
    Е
    2.27
    ことが多い
    2.25
    ে
    2.23
    i
    2.17
    Act Density 0.295%

    No Known Activations