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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash

    The neuron is keyed to spotting in-text example markers and enumerations—essentially phrases like “for example” (and the immediately surrounding commas) that introduce illustrative examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ocused
    -0.06
    Equals
    -0.06
     elem
    -0.06
     Knee
    -0.06
     borderBottom
    -0.06
     OT
    -0.06
    ame
    -0.06
    .header
    -0.06
    SHOT
    -0.06
     tour
    -0.06
    POSITIVE LOGITS
    /admin
    0.07
    -↵↵
    0.07
    aml
    0.07
    _PORT
    0.07
     "),
    0.06
    uft
    0.06
    _chars
    0.06
    ibal
    0.06
    иж
    0.06
    MessageBox
    0.06
    Act Density 0.016%

    No Known Activations