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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash

    The neuron activates on identifier tokens naming list‐ or queue‐valued members or methods (e.g. anything ending in “List” or “Queue”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ваем
    -0.07
     shade
    -0.06
    David
    -0.06
     Alexand
    -0.06
    admins
    -0.06
    461
    -0.06
    .Serve
    -0.06
    goals
    -0.06
     Бер
    -0.06
    _Char
    -0.06
    POSITIVE LOGITS
    ALLERY
    0.07
     productList
    0.07
    담
    0.07
    owell
    0.06
    analy
    0.06
     etiqu
    0.06
    але
    0.06
     кал
    0.06
    .forChild
    0.06
     vaginal
    0.06
    Act Density 0.022%

    No Known Activations