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

    Neuronpedia

    INDEX
    Explanations

    swap or exchange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     progression
    0.88
     branching
    0.77
     graded
    0.77
    LessThan
    0.75
     वर्गीकृत
    0.71
    Sorted
    0.70
     ಹೊಂದಿದೆ
    0.70
    っていく
    0.69
     hierarchy
    0.69
    முத
    0.69
    POSITIVE LOGITS
     swap
    2.21
     Swap
    2.21
    swap
    2.18
     swapping
    2.06
    Swap
    2.06
    交换
    1.94
     swaps
    1.86
     swapped
    1.85
     interchange
    1.77
     perm
    1.76
    Act Density 0.079%

    No Known Activations