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

    Neuronpedia

    INDEX
    Explanations

    say "√"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /\
    0.47
    =$\
    0.44
    )/\
    0.43
    /√
    0.42
     Wurzel
    0.42
    โค
    0.39
     Root
    0.38
    }/\
    0.38
     મૂળ
    0.38
     }{\
    0.37
    POSITIVE LOGITS
     routes
    1.36
     route
    1.27
     Routes
    1.10
    routes
    1.09
    Route
    1.08
    Routes
    1.08
     кор
    1.05
    route
    1.03
     Route
    1.01
    路由
    1.00
    Act Density 0.001%

    No Known Activations