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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elif
    -0.07
    (trim
    -0.07
     wc
    -0.07
     avait
    -0.07
    USART
    -0.06
    Vectors
    -0.06
     pruning
    -0.06
    420
    -0.06
    	Double
    -0.06
     MAIN
    -0.06
    POSITIVE LOGITS
     Puzzle
    0.06
     signup
    0.06
     Offering
    0.06
    TED
    0.06
    ури
    0.06
    plies
    0.06
    anism
    0.06
    sealed
    0.06
     Sydney
    0.06
    .INSTANCE
    0.06
    Act Density 0.086%

    No Known Activations