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

    Neuronpedia

    INDEX
    Explanations

    route

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bed
    -0.06
    .special
    -0.06
     praising
    -0.06
     Lily
    -0.06
    Hyper
    -0.06
    175
    -0.06
     clans
    -0.06
    Tan
    -0.06
     hard
    -0.06
     boards
    -0.06
    POSITIVE LOGITS
     route
    0.10
     routes
    0.09
    (route
    0.08
    _route
    0.08
    CONT
    0.08
     Route
    0.08
    router
    0.08
     Rout
    0.08
    \Routing
    0.07
    outing
    0.07
    Act Density 0.020%

    No Known Activations