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

    Neuronpedia

    INDEX
    Explanations

    II

    np_max-act · gemini-2.0-flash

    The neuron detects major section headings marked by Roman‐numeral outline labels (e.g. “I.” at the start of a section).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .End
    -0.06
     CP
    -0.06
    ’ın
    -0.06
     lok
    -0.06
    hus
    -0.06
    orida
    -0.06
    áty
    -0.06
    ená
    -0.06
     Mang
    -0.06
    qp
    -0.06
    POSITIVE LOGITS
    _w
    0.07
    _tasks
    0.06
    层
    0.06
    stringstream
    0.06
    _atom
    0.06
    Pixmap
    0.06
    ()=>{↵
    0.06
    0.06
    _Space
    0.06
    arged
    0.06
    Act Density 0.004%

    No Known Activations