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

    Neuronpedia

    INDEX
    Explanations

    ]\

    np_max-act · gemini-2.0-flash

    This neuron detects in‐text citation markers (e.g. “[[@CR1]\]”) and their surrounding punctuation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Whereas
    -0.07
    _PACK
    -0.07
    Stripe
    -0.07
     loại
    -0.07
     lakes
    -0.06
     Pence
    -0.06
     pops
    -0.06
     immature
    -0.06
     ICON
    -0.06
     stares
    -0.06
    POSITIVE LOGITS
    博物
    0.06
     Ng
    0.06
     Aleppo
    0.06
     chaque
    0.06
     논
    0.06
    .Modules
    0.06
     mpi
    0.06
     Doğum
    0.06
     Ос
    0.06
     Naomi
    0.06
    Act Density 0.026%

    No Known Activations