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

    Neuronpedia

    INDEX
    Explanations

    graph connectivity and networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    辕
    0.55
    噘
    0.54
     pakaian
    0.53
     impuestos
    0.52
     Yogurt
    0.52
     옷
    0.51
     Doremi
    0.51
     yogurt
    0.50
     женщина
    0.50
     ProRes
    0.50
    POSITIVE LOGITS
     connectivity
    1.09
     graph
    1.08
     topological
    1.02
    Graph
    1.01
    Connectivity
    1.00
    Network
    0.99
     network
    0.98
     networks
    0.97
     nodes
    0.95
     topology
    0.94
    Act Density 0.143%

    No Known Activations