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

    Neuronpedia

    INDEX
    Explanations

    readability and ease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पॉपुलर
    0.40
     nacional
    0.40
     temporada
    0.39
    spiele
    0.39
     celebrar
    0.39
    spielen
    0.38
    celona
    0.38
     públic
    0.37
     nacionais
    0.37
    ្ឋ
    0.37
    POSITIVE LOGITS
    阅读
    0.59
     comprehension
    0.59
     readability
    0.57
     чита
    0.57
     Reading
    0.55
     Compre
    0.55
     reading
    0.53
     đọc
    0.53
    读
    0.52
     читать
    0.50
    Act Density 0.484%

    No Known Activations