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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash

    The neuron fires on document-level framing or discourse markers—words that introduce or highlight the authors’ aims, purpose, or key points (e.g. “however,” “purpose,” “note,” “highlight,” “aim,” “significance”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    shows
    -0.08
     RT
    -0.07
     EACH
    -0.06
    SZ
    -0.06
     show
    -0.06
    Recording
    -0.06
     refine
    -0.06
    ステ
    -0.06
    :X
    -0.06
     false
    -0.06
    POSITIVE LOGITS
     Mitsubishi
    0.07
    "/>
    0.06
    .Html
    0.06
    0.06
    líb
    0.06
     THC
    0.06
    fü
    0.06
    _Core
    0.06
     çalışmalar
    0.06
     모든
    0.06
    Act Density 0.031%

    No Known Activations