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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on the introductory “To …” phrase (e.g. “To merge…,” “To resize…,” “To calculate…,” etc.) that kicks off a how-to explanation in the assistant’s responses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code examples related to reading data from CSV files in Python.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Requirement
    -0.06
    achat
    -0.06
    .encoding
    -0.06
     OCD
    -0.06
    惑
    -0.06
    .ol
    -0.06
     guidance
    -0.06
    �
    -0.06
     booking
    -0.06
     newspapers
    -0.06
    POSITIVE LOGITS
     제작
    0.07
    ServerError
    0.07
    magnitude
    0.06
     상세
    0.06
    ymce
    0.06
     hm
    0.06
    GetPosition
    0.06
     SAF
    0.06
     عملیات
    0.06
    міністра
    0.06
    Act Density 0.024%

    No Known Activations