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 is triggered by mentions of computer memory concepts (e.g. “memory,” “RAM,” “swap”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (passport
    -0.07
     Video
    -0.07
    -gun
    -0.06
    $↵
    -0.06
     driver
    -0.06
     stehen
    -0.06
     بوده
    -0.06
     squared
    -0.06
     включ
    -0.06
     khỏe
    -0.06
    POSITIVE LOGITS
    check
    0.07
     tal
    0.07
    =url
    0.07
    赶
    0.07
    .xyz
    0.07
     Trim
    0.06
     是
    0.06
    름
    0.06
    table
    0.06
     destined
    0.06
    Act Density 0.011%

    No Known Activations