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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    This neuron detects numeric citation markers (e.g. volume and page numbers and their separators in references).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     문
    -0.07
     Benz
    -0.07
     png
    -0.07
    415
    -0.07
    (PARAM
    -0.07
    Proxy
    -0.06
     信
    -0.06
     difficulties
    -0.06
    285
    -0.06
    Provides
    -0.06
    POSITIVE LOGITS
    ">'.$
    0.07
    .BadRequest
    0.06
     Inspiration
    0.06
     BadRequest
    0.06
     tä
    0.06
     daunting
    0.06
     spaghetti
    0.06
     PARA
    0.06
    cação
    0.06
     nous
    0.06
    Act Density 0.008%

    No Known Activations