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

    Neuronpedia

    INDEX
    Explanations

    describing ideas and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    প্ট
    1.17
     dostępne
    1.15
    ক
    1.10
    ,$$
    1.05
    czne
    1.04
    axies
    1.03
    Emergency
    1.01
    HING
    0.99
    cje
    0.98
     ży
    0.97
    POSITIVE LOGITS
    柔軟
    0.97
    та
    0.96
    тяну
    0.90
     thoughtfully
    0.89
    ваны
    0.88
     सरस्व
    0.88
    وسیع
    0.87
     metabol
    0.87
    ьте
    0.87
    ڕۆ
    0.86
    Act Density 0.000%

    No Known Activations