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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on high-frequency function words—especially prepositions and articles (e.g. “for,” “with,” “to,” “in,” “the,” “a”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _chg
    -0.07
    地区
    -0.07
    .Initialize
    -0.07
    Change
    -0.07
     furthermore
    -0.06
    -array
    -0.06
    getState
    -0.06
    (mode
    -0.06
     meget
    -0.06
    itori
    -0.06
    POSITIVE LOGITS
    /foo
    0.06
     partir
    0.06
     Rutgers
    0.06
     jr
    0.06
     Economist
    0.06
    _At
    0.06
    YRO
    0.06
    (@
    0.06
    _REAL
    0.06
    ='{
    0.06
    Act Density 0.141%

    No Known Activations