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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الملابس
    0.47
    黢
    0.45
     маркетин
    0.42
     时尚
    0.42
    饰演
    0.41
    蜮
    0.41
     ব্যবহার
    0.40
     ఎలా
    0.40
    褂
    0.40
    购物
    0.40
    POSITIVE LOGITS
    K
    0.47
     P
    0.42
     N
    0.39
     S
    0.39
     \
    0.39
     {
    0.39
     n
    0.38
    {\
    0.38
    6
    0.38
    5
    0.38
    Act Density 0.118%

    No Known Activations