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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_max-act · gemini-2.0-flash

    The neuron activates on numbered list markers (e.g. “1.”, “2.”, etc.) in procedural or step‐by‐step descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     أكثر
    -0.08
    itals
    -0.07
    vič
    -0.06
     jclass
    -0.06
     Conditioning
    -0.06
    izio
    -0.06
     chip
    -0.06
     Latest
    -0.06
     measurable
    -0.06
    ьи
    -0.06
    POSITIVE LOGITS
     arşiv
    0.06
     ren
    0.06
     risen
    0.06
     grav
    0.06
     gained
    0.06
     thiên
    0.06
     Guild
    0.06
     guild
    0.06
    (`${
    0.06
     tiến
    0.06
    Act Density 0.056%

    No Known Activations