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

    Neuronpedia

    INDEX
    Explanations

    vivid descriptions or pictures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਼
    0.47
     primacy
    0.45
     derogatory
    0.42
    silyl
    0.41
     predominant
    0.41
     خصوصی
    0.40
    ляю
    0.40
     admissible
    0.39
    ਤ
    0.39
    க்கார
    0.39
    POSITIVE LOGITS
     熱
    0.46
     temperatur
    0.43
     encuent
    0.43
     কেঁ
    0.43
     ngunit
    0.43
     雪
    0.42
     permitió
    0.42
     nhưng
    0.42
     sağlay
    0.42
     温度
    0.41
    Act Density 0.002%

    No Known Activations