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

    Neuronpedia

    INDEX
    Explanations

    mathematical sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contaminants
    -0.08
    \x
    -0.08
     contamin
    -0.08
     thereby
    -0.08
     Bates
    -0.07
     प्रश
    -0.07
    وز
    -0.07
     roadmap
    -0.07
     ه
    -0.07
    plug
    -0.07
    POSITIVE LOGITS
    번째
    0.09
     naman
    0.09
     представля
    0.08
     [],
    0.08
     ואני
    0.08
     captura
    0.08
     czyli
    0.08
     denotes
    0.08
     发
    0.08
     Minecraft
    0.08
    Act Density 0.104%

    No Known Activations