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

    Neuronpedia

    INDEX
    Explanations

    function words

    np_max-act · gemini-2.0-flash

    The neuron activates on common function words—short grammatical connectors like articles, prepositions, and conjunctions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    URITY
    -0.07
    љ
    -0.07
     Both
    -0.07
     ')
    -0.07
     Budd
    -0.06
    OSE
    -0.06
    NAV
    -0.06
     toJSON
    -0.06
     VER
    -0.06
     unload
    -0.06
    POSITIVE LOGITS
    สาม
    0.07
    (stream
    0.06
     fileType
    0.06
    ospels
    0.06
    _star
    0.06
    国家
    0.06
     知
    0.06
     phosphory
    0.06
     alternatively
    0.06
     قم
    0.06
    Act Density 0.032%

    No Known Activations