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

    Neuronpedia

    INDEX
    Explanations

    routing web requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kohler
    0.71
     demoral
    0.70
     jail
    0.67
    Durham
    0.63
     justified
    0.63
    يديا
    0.63
     deserving
    0.63
    该公司
    0.62
     Supplement
    0.62
    डेंगू
    0.62
    POSITIVE LOGITS
     routes
    2.14
    routes
    2.12
    Routes
    2.05
     Routes
    2.02
     route
    1.94
     Route
    1.91
    route
    1.90
    Route
    1.89
    路由
    1.86
    Router
    1.63
    Act Density 0.219%

    No Known Activations