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

    Neuronpedia

    INDEX
    Explanations

    tree traversal orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.75
    US
    0.72
    8
    0.70
    3
    0.68
    ur
    0.68
    ah
    0.67
    9
    0.66
    1
    0.66
    5
    0.66
    4
    0.65
    POSITIVE LOGITS
     vértice
    0.58
    的管理
    0.58
     descendant
    0.56
     traversal
    0.56
     recorrido
    0.55
     interviewed
    0.55
     पाती
    0.55
     treetops
    0.54
     vertex
    0.54
    ეთი
    0.53
    Act Density 0.014%

    No Known Activations