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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of memory requirements or memory usage.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    —for
    -0.07
     picnic
    -0.07
    ico
    -0.07
    .constraints
    -0.06
    adium
    -0.06
     fundamentals
    -0.06
     صند
    -0.06
     　 　
    -0.06
    _clock
    -0.06
     hieronta
    -0.06
    POSITIVE LOGITS
    ookeeper
    0.07
    Sac
    0.07
     ।↵
    0.06
     cuer
    0.06
     utilize
    0.06
    uí
    0.06
    Files
    0.06
    asmine
    0.06
     Lat
    0.06
     Ped
    0.06
    Act Density 0.014%

    No Known Activations