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

    Neuronpedia

    INDEX
    Explanations

    network routing paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    盒
    -0.10
     interactieve
    -0.09
     workshop
    -0.09
     interactive
    -0.09
     boxed
    -0.09
    字体
    -0.08
     Workshop
    -0.08
     boxes
    -0.08
     screenplay
    -0.08
     Taschen
    -0.08
    POSITIVE LOGITS
     routing
    0.13
     preferential
    0.12
    Routing
    0.12
    routing
    0.11
    /routes
    0.11
     Routing
    0.11
     routes
    0.11
     outages
    0.10
     маршру
    0.10
    mux
    0.10
    Act Density 0.013%

    No Known Activations