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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects the "return" keyword in React/JSX code blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ppard
    -0.07
     Plus
    -0.07
     dared
    -0.06
     Explore
    -0.06
    yp
    -0.06
     investigation
    -0.06
    .Bad
    -0.06
     sentenced
    -0.06
     supervised
    -0.06
     Mechanical
    -0.06
    POSITIVE LOGITS
    _ROT
    0.06
    ıda
    0.06
    	return
    0.06
    off
    0.06
     metod
    0.06
    .assertNot
    0.06
    'ét
    0.06
    těl
    0.06
    uart
    0.06
    вей
    0.06
    Act Density 0.002%

    No Known Activations