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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially counts, percentages, and other figures—highlighting statistics and enumerations in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,
↵
    -0.07
    لح
    -0.06
    、中
    -0.06
     Sense
    -0.06
     song
    -0.06
    letes
    -0.06
    ドル
    -0.06
     lime
    -0.06
    .'''↵
    -0.06
    ɵ
    -0.06
    POSITIVE LOGITS
    Visual
    0.07
    .robot
    0.06
    _individual
    0.06
    DataType
    0.06
    �认
    0.06
    _fragment
    0.06
     해결
    0.06
     sık
    0.06
    GreaterThan
    0.06
     Bitte
    0.06
    Act Density 0.037%

    No Known Activations