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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    The neuron fires on the document’s section-heading identifiers (e.g. the “{#s2}” markers that label the Methods section).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .usage
    -0.07
    weigh
    -0.06
    });↵
    -0.06
     ràng
    -0.06
     Raptors
    -0.06
    .photos
    -0.06
     kıs
    -0.06
    �
    -0.06
    Exposed
    -0.06
     Tracks
    -0.06
    POSITIVE LOGITS
     appeared
    0.07
    SG
    0.07
     sympathetic
    0.07
    opathy
    0.07
     volcanic
    0.06
     COLL
    0.06
    coordinate
    0.06
     дли
    0.06
     restTemplate
    0.06
    632
    0.06
    Act Density 0.000%

    No Known Activations