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

    Neuronpedia

    INDEX
    Explanations

    oxidation/chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     water
    -0.66
     hyd
    -0.56
     समीक्षक
    -0.51
     hydro
    -0.49
     Hydro
    -0.47
      
    -0.45
    quias
    -0.45
     swim
    -0.45
     Water
    -0.44
     hidro
    -0.44
    POSITIVE LOGITS
     étoit
    0.66
     NDEBUG
    0.64
     بيها
    0.63
     feroit
    0.62
     onOptions
    0.62
     tjen
    0.62
     pouvoit
    0.61
    PageRoute
    0.60
     enfans
    0.60
    WebServlet
    0.60
    Act Density 0.021%

    No Known Activations