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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agraph
    -0.09
    _graph
    -0.08
     graph
    -0.08
    research
    -0.08
     Graph
    -0.08
    .Graph
    -0.08
     boîte
    -0.08
    .graph
    -0.08
     conex
    -0.08
    Graph
    -0.08
    POSITIVE LOGITS
     uw
    0.09
     mukuru
    0.08
     Ramp
    0.08
     vaz
    0.08
    ṱ
    0.08
     fades
    0.08
     faded
    0.08
     aanbevel
    0.08
     Verst
    0.08
     നഷ്ട
    0.08
    Act Density 0.001%

    No Known Activations