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

    Neuronpedia

    INDEX
    Explanations

    availability through channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conseguiu
    0.41
     census
    0.40
     gegevens
    0.39
    версите
    0.38
    ştur
    0.38
    DataGridView
    0.38
    iscus
    0.38
    িয়ার
    0.38
    utions
    0.38
    opyran
    0.38
    POSITIVE LOGITS
    دا
    0.47
     meliputi
    0.47
     للنساء
    0.44
     Mau
    0.43
    २
    0.43
    իր
    0.42
     trois
    0.42
    Χ
    0.40
     ٢
    0.40
    只限
    0.39
    Act Density 0.000%

    No Known Activations