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

    Neuronpedia

    INDEX
    Explanations

    crossing legs or boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ry
    0.65
    า
    0.60
    ا
    0.59
    p
    0.58
    N
    0.56
    ي
    0.55
    K
    0.54
    MR
    0.54
    o
    0.54
    FName
    0.52
    POSITIVE LOGITS
    交叉
    1.11
     cross
    1.09
     crossing
    1.08
    cross
    1.02
     crossed
    1.00
     crosses
    1.00
     क्रॉस
    0.96
     crossings
    0.96
    crossed
    0.95
    Cross
    0.93
    Act Density 0.134%

    No Known Activations