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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash

    This neuron detects placeholder fields in curly braces for menu items (e.g. `{appetizer name}`, `{beverage name}`, `{entree 1 name}`, `{dessert name}`, `{total cost}`) in an order‐taking template.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ONE
    -0.06
    .Device
    -0.06
     مرتبط
    -0.06
    +"'
    -0.06
     Lup
    -0.06
     повтор
    -0.06
    POWER
    -0.06
     sweeping
    -0.06
     darauf
    -0.06
    NEXT
    -0.06
    POSITIVE LOGITS
    qn
    0.07
     condiciones
    0.06
    imas
    0.06
    鹿
    0.06
     أفضل
    0.06
    PLEMENT
    0.06
    inidad
    0.06
    ้จ
    0.06
    UpDown
    0.06
    _blk
    0.06
    Act Density 0.028%

    No Known Activations