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

    Neuronpedia

    INDEX
    Explanations

    swapping elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    0.54
     vier
    0.45
    archiwizowane
    0.45
    segaretro
    0.45
    utiérrez
    0.44
    éroport
    0.44
    ാന
    0.44
    Berat
    0.43
     każde
    0.43
    вершена
    0.43
    POSITIVE LOGITS
     swapping
    0.56
     swapped
    0.52
     swap
    0.52
     move
    0.48
     Swap
    0.47
     group
    0.45
     swaps
    0.45
     substitution
    0.44
     left
    0.44
     moved
    0.44
    Act Density 0.109%

    No Known Activations