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

    Neuronpedia

    INDEX
    Explanations

    multilingual code or text snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     шаг
    0.69
    प्पो
    0.65
     crowd
    0.62
    質感
    0.61
     vrat
    0.59
     大きい
    0.58
     закон
    0.57
    ถา
    0.57
     rewards
    0.57
     water
    0.56
    POSITIVE LOGITS
    ்த
    0.68
    dessous
    0.66
    <div>
    0.66
    <unused758>
    0.65
    дары
    0.64
     لپاره
    0.61
    жению
    0.60
    ವರೆಗೆ
    0.59
    ovia
    0.58
     COULD
    0.57
    Act Density 0.454%

    No Known Activations