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

    Neuronpedia

    INDEX
    Explanations

    class="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    withstanding
    0.35
    ਦੀ
    0.34
     Как
    0.34
    десь
    0.33
     hotspots
    0.32
     то
    0.32
     Же
    0.32
    ्स
    0.31
    묘
    0.31
    ′,
    0.30
    POSITIVE LOGITS
    ibilités
    0.33
    ień
    0.32
    ्रीय
    0.31
     वाले
    0.30
    tela
    0.29
     Majesty
    0.29
    ogen
    0.29
    À
    0.29
    Probability
    0.29
     população
    0.29
    Act Density 0.152%

    No Known Activations