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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of C++ dynamic‐memory allocation (the “new” operator) and related allocation‐failure contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ура
    -0.07
    htaking
    -0.06
    워
    -0.06
     آموز
    -0.06
     Eduardo
    -0.06
    ‌س
    -0.06
    その他
    -0.06
    manuel
    -0.06
    ypical
    -0.06
     courageous
    -0.06
    POSITIVE LOGITS
     advertis
    0.06
     Flowers
    0.06
    alloca
    0.06
    .twitter
    0.06
     digits
    0.06
     cler
    0.06
     rer
    0.06
     джер
    0.06
     Chem
    0.06
     SOP
    0.06
    Act Density 0.003%

    No Known Activations