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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects instructions about gathering complete information—phrases telling the assistant to ask questions or capture “all the information you need.”

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

    requests for technical specifications and implementation details.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nose
    -0.07
     estim
    -0.07
    ()->
    -0.07
    Testing
    -0.07
    arrays
    -0.07
    "]
    -0.06
    cents
    -0.06
    endi
    -0.06
    conde
    -0.06
    _urls
    -0.06
    POSITIVE LOGITS
     pornost
    0.06
    лоп
    0.06
    .getLongitude
    0.06
    prav
    0.06
     bv
    0.06
     Wouldn
    0.06
    	window
    0.06
     allergic
    0.06
    .ease
    0.06
    buttonShape
    0.06
    Act Density 0.194%

    No Known Activations