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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act · gemini-2.0-flash

    The neuron detects bibliographic and cartographic reference terms—words and headings related to mapping citations, map scales, and geographic data sources.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Unlike
    -0.07
     öldür
    -0.07
    KANJI
    -0.06
     kardeş
    -0.06
    vertiser
    -0.06
    gos
    -0.06
    زا
    -0.06
    眼睛
    -0.06
    ARNING
    -0.06
     Months
    -0.06
    POSITIVE LOGITS
     円
    0.06
    會
    0.06
    duğ
    0.06
     )(
    0.06
     Represents
    0.06
    می
    0.06
    >>>
    0.06
    ([
↵
    0.06
     digest
    0.06
     cli
    0.06
    Act Density 0.006%

    No Known Activations