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

    Neuronpedia

    INDEX
    Explanations

    products

    np_max-act · gemini-2.0-flash

    The neuron detects promotional language emphasizing the provision of high-quality products and services.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    해야
    -0.07
     schemes
    -0.07
    RL
    -0.06
    opathy
    -0.06
     côt
    -0.06
    �
    -0.06
    Errors
    -0.06
    []"
    -0.06
    .raise
    -0.05
    cli
    -0.05
    POSITIVE LOGITS
    liqu
    0.07
    pps
    0.07
     Francie
    0.07
     BAB
    0.07
     intrigue
    0.07
    (component
    0.07
     ViewData
    0.07
     recruited
    0.06
    aybe
    0.06
    .device
    0.06
    Act Density 0.037%

    No Known Activations