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

    Neuronpedia

    INDEX
    Explanations

    Data transfer operations

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers and event names related to “load” operations—especially tokens like LoadCompleted, LoadProgress, DataLoad, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     کردند
    -0.07
    附
    -0.07
    시간
    -0.07
    lam
    -0.06
    .RightToLeft
    -0.06
     안
    -0.06
    _VAL
    -0.06
    ुँ
    -0.06
     인구
    -0.06
    Sale
    -0.06
    POSITIVE LOGITS
     entails
    0.07
     lure
    0.06
    ]]];↵
    0.06
    운
    0.06
     ;
↵
    0.06
     whales
    0.06
    -operative
    0.06
     Within
    0.06
    Tau
    0.06
    imension
    0.06
    Act Density 0.022%

    No Known Activations