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

    Neuronpedia

    INDEX
    Explanations

    linked list structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TREE
    0.57
     Tree
    0.56
    Tree
    0.54
     Trees
    0.52
     tree
    0.52
     पेड़ों
    0.52
    树
    0.51
     arbre
    0.51
     trees
    0.49
     дерево
    0.49
    POSITIVE LOGITS
     carry
    0.73
    carry
    0.71
    Merge
    0.57
    Carry
    0.57
     merging
    0.56
     Carry
    0.56
     merger
    0.55
     carries
    0.54
     carried
    0.53
     merge
    0.53
    Act Density 0.012%

    No Known Activations