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

    Neuronpedia

    INDEX
    Explanations

    savings

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens containing decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ThreadPool
    -0.07
    .Run
    -0.07
     manifested
    -0.07
     honoured
    -0.07
     Ensemble
    -0.07
     Gi�
    -0.07
     phase
    -0.07
    Polygon
    -0.07
     Florence
    -0.07
    .INT
    -0.07
    POSITIVE LOGITS
     savings
    0.11
     Savings
    0.09
    avings
    0.08
     سكان
    0.07
    tax
    0.07
    акс
    0.06
     imkân
    0.06
     Вс
    0.06
     حک
    0.06
    Sales
    0.06
    Act Density 0.002%

    No Known Activations