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

    Neuronpedia

    INDEX
    Explanations

    purpose for collecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दब
    0.43
    同样
    0.42
    挀
    0.41
    budget
    0.41
    inados
    0.40
    busters
    0.39
    endants
    0.38
    percayaan
    0.38
     idem
    0.38
    eties
    0.38
    POSITIVE LOGITS
    Де
    0.47
     aastal
    0.45
    ."
    0.45
    For
    0.43
    Фор
    0.43
    О
    0.42
     Warszawie
    0.42
     RCLCPP
    0.42
     Abelian
    0.41
    Dear
    0.40
    Act Density 0.000%

    No Known Activations