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

    Neuronpedia

    INDEX
    Explanations

    tree of thought, prediction, data structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivité
    0.41
    currentIndex
    0.40
     появи
    0.39
     হুমায়
    0.39
     repatri
    0.39
     dances
    0.39
    elens
    0.38
    pozy
    0.38
    ])*
    0.38
    வையில்
    0.38
    POSITIVE LOGITS
     tree
    0.93
     Tree
    0.86
    🌲
    0.76
    Tree
    0.75
    树
    0.72
     Trees
    0.70
     trees
    0.70
     Stump
    0.70
     arbres
    0.69
    🌳
    0.68
    Act Density 0.012%

    No Known Activations