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

    Neuronpedia

    INDEX
    Explanations

    evaluation and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ởi
    0.44
    Yun
    0.42
     DHT
    0.41
     involuc
    0.41
     Rahman
    0.40
    వె
    0.39
     ഒ
    0.39
     Yun
    0.39
     Lea
    0.39
     Youn
    0.38
    POSITIVE LOGITS
    accès
    0.45
    的重要性
    0.41
     natürlich
    0.40
    standard
    0.39
     gün
    0.39
     standard
    0.39
    access
    0.39
    disable
    0.39
    importance
    0.38
    invest
    0.38
    Act Density 0.000%

    No Known Activations