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

    Neuronpedia

    INDEX
    Explanations

    citation markers

    np_max-act · gemini-2.0-flash

    The neuron detects in‐text reference citations (e.g. “[​@CR…]”) in scholarly writing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _txt
    -0.07
     สร
    -0.07
     removeFromSuperview
    -0.07
    ━━
    -0.07
    .zz
    -0.06
    ]-
    -0.06
     vardır
    -0.06
     قرآن
    -0.06
    )-(
    -0.06
    itori
    -0.06
    POSITIVE LOGITS
     magnet
    0.07
     sexle
    0.06
     planetary
    0.06
    !',↵
    0.06
    pointer
    0.06
     strategist
    0.06
     Guards
    0.06
     Ship
    0.06
     moo
    0.06
    numbers
    0.06
    Act Density 0.010%

    No Known Activations