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

    Neuronpedia

    INDEX
    Explanations

    spending Congress has approved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urdy
    0.49
    鹑
    0.47
    يله
    0.47
    辕
    0.47
    दारी
    0.47
    শায়
    0.45
    ள்ளார்
    0.44
    щих
    0.43
     mobilise
    0.43
    urator
    0.43
    POSITIVE LOGITS
     trivia
    0.44
     migrations
    0.43
     FAQ
    0.41
     ווי
    0.40
    را
    0.39
    ائ
    0.39
    Append
    0.39
    ها
    0.38
    }-
    0.38
     தட
    0.38
    Act Density 0.002%

    No Known Activations