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

    Neuronpedia

    INDEX
    Explanations

    "Hope this is helpful"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     こんにちは
    0.55
     лично
    0.55
    ...">
    0.55
    唕
    0.55
     있어요
    0.54
    腼
    0.54
     \...
    0.54
    秪
    0.54
     chiede
    0.54
     Одна
    0.53
    POSITIVE LOGITS
    উল্লেখ্য
    0.50
     data
    0.49
    unn
    0.48
     keys
    0.48
     related
    0.48
    toRadians
    0.48
     resized
    0.48
     shards
    0.47
    <eos>
    0.46
     helpful
    0.46
    Act Density 0.242%

    No Known Activations