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

    Neuronpedia

    INDEX
    Explanations

    links and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wości
    0.41
     Sentiment
    0.41
    મિત
    0.41
     живу
    0.40
     sentiment
    0.39
    locationY
    0.39
     selectedCard
    0.39
     ডেভেল
    0.39
    緯
    0.39
     cosmological
    0.38
    POSITIVE LOGITS
    ?!
    0.42
    N
    0.42
    includes
    0.38
    Cases
    0.38
    use
    0.37
    Double
    0.37
    carousel
    0.36
    itaire
    0.36
    Ū
    0.36
    ジェ
    0.35
    Act Density 0.001%

    No Known Activations