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

    Neuronpedia

    INDEX
    Explanations

    describe

    np_max-act · gemini-2.0-flash

    This neuron activates on requests or statements about describing or discussing images (e.g. tokens like “describe,” “images,” and their equivalents in other languages).

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

    phrases about the creation and description of images.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .setOnClickListener
    -0.07
    _REQUIRED
    -0.06
     OWNER
    -0.06
    Manual
    -0.06
    _outputs
    -0.06
    _images
    -0.06
    	K
    -0.06
     agreement
    -0.06
    办
    -0.06
     Conference
    -0.06
    POSITIVE LOGITS
     رق
    0.06
     xu
    0.06
     satın
    0.06
    ekkür
    0.06
    $time
    0.06
     tolerance
    0.06
     Jays
    0.06
     biraz
    0.06
    _cate
    0.06
    describe
    0.06
    Act Density 0.032%

    No Known Activations