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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    The neuron fires on C++ template‐metaprogramming container names (e.g. “map”, “list”, “deque”, “set”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Với
    -0.06
    ird
    -0.06
    iliated
    -0.06
    .publish
    -0.06
     Brit
    -0.06
     invaded
    -0.06
     tươi
    -0.06
     sınıf
    -0.06
     dif
    -0.06
    ิค
    -0.06
    POSITIVE LOGITS
    (sym
    0.07
    _EXTRA
    0.06
     inaccurate
    0.06
    ї
    0.06
     POSSIBILITY
    0.06
     priceless
    0.06
    gam
    0.06
     가능
    0.06
    ;"><
    0.06
    datum
    0.06
    Act Density 0.001%

    No Known Activations