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

    Neuronpedia

    INDEX
    Explanations

    vention

    np_max-act · gemini-2.0-flash

    The neuron detects the word “Invention” (as in the “Field of Invention” heading) in patent-style documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    자인
    -0.07
     personalities
    -0.07
    .readAs
    -0.07
    orous
    -0.07
     등장
    -0.06
     Miles
    -0.06
     चलत
    -0.06
     نش
    -0.06
     stares
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _NO
    0.07
    (dataSource
    0.06
    expert
    0.06
    gression
    0.06
     специалист
    0.06
    _percent
    0.06
    918
    0.06
    /Dk
    0.06
    username
    0.06
    getSource
    0.06
    Act Density 0.000%

    No Known Activations