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

    Neuronpedia

    INDEX
    Explanations

    introspection and concern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    উন্ড
    0.50
    స్
    0.45
    AL
    0.44
    Rocket
    0.44
    Skeleton
    0.43
    :
    0.43
    贵的
    0.42
     PLANT
    0.41
    Short
    0.41
    ப்ஸ்
    0.41
    POSITIVE LOGITS
     Afric
    0.48
     सामान्य
    0.48
    困難
    0.46
     συνο
    0.46
     सम
    0.43
     Job
    0.43
     สนาม
    0.43
    0.43
     آنها
    0.41
     ময়
    0.41
    Act Density 0.002%

    No Known Activations