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

    Neuronpedia

    INDEX
    Explanations

    graph, graphs, graphing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    é
    1.31
    gten
    1.17
    are
    1.15
    ge
    1.09
    os
    1.07
    ut
    1.05
    ؟.
    1.00
    م
    0.98
     are
    0.97
     परामर्श
    0.97
    POSITIVE LOGITS
     graph
    1.51
    '
    1.47
    ות
    1.41
     subgraph
    1.38
     Graph
    1.27
     graf
    1.23
     Graf
    1.14
    ing
    1.13
    ال
    1.12
    u
    1.11
    Act Density 0.028%

    No Known Activations