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

    Neuronpedia

    INDEX
    Explanations

    graphs and networkx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lotion
    -0.09
     hypnosis
    -0.09
     sweat
    -0.09
     dosis
    -0.09
     bodily
    -0.09
    Milk
    -0.09
    Luxury
    -0.09
    Responses
    -0.09
     whipped
    -0.09
     physician
    -0.09
    POSITIVE LOGITS
     adjacency
    0.19
    (Graph
    0.14
    (vertices
    0.14
     graph
    0.14
    .vertices
    0.14
    _vertices
    0.14
    (graph
    0.13
    Vertices
    0.13
     graphs
    0.13
    .Graph
    0.13
    Act Density 0.019%

    No Known Activations