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

    Neuronpedia

    INDEX
    Explanations

    restricted vs simple comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ┙
    0.45
    ί
    0.43
    лиза
    0.43
     fréquence
    0.41
    στά
    0.41
    频繁
    0.41
    ன்
    0.41
    ù
    0.40
    omonas
    0.40
    ﹡
    0.39
    POSITIVE LOGITS
     ಈಗ
    0.45
    発表
    0.41
     autism
    0.40
     nurseries
    0.40
     Domestic
    0.39
     ऑलरेडी
    0.39
     clues
    0.39
     Autism
    0.39
     EPL
    0.39
    পুর
    0.39
    Act Density 0.004%

    No Known Activations