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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the word “Get” (as in code comments/instruction lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sont
    -0.07
     Honduras
    -0.07
    _SEC
    -0.06
     قوان
    -0.06
     mattresses
    -0.06
     Doming
    -0.06
     也
    -0.06
     продукт
    -0.06
    Encoding
    -0.06
    닥
    -0.06
    POSITIVE LOGITS
    Getty
    0.07
    CID
    0.07
     GK
    0.07
     Celebrity
    0.07
    ./
    0.06
    queda
    0.06
    :'',↵
    0.06
    ullan
    0.06
    ‘s
    0.06
    elcome
    0.06
    Act Density 0.029%

    No Known Activations