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

    Neuronpedia

    INDEX
    Explanations

    React routing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jane
    0.86
    Jane
    0.75
     Elizabeth
    0.69
    jane
    0.67
     কচ
    0.67
     Flore
    0.67
     koron
    0.65
    Elizabeth
    0.65
     Viscount
    0.65
     Green
    0.64
    POSITIVE LOGITS
     Router
    2.16
     router
    2.16
    router
    2.11
    Router
    2.07
     routers
    2.05
     Routes
    1.89
    Routes
    1.88
     routes
    1.86
    routers
    1.85
     routing
    1.83
    Act Density 0.079%

    No Known Activations