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

    Neuronpedia

    INDEX
    Explanations

    Citation markers

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect numeric data, especially decimal numbers and quantitative measurements in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crises
    -0.07
    .Management
    -0.07
     datePicker
    -0.07
     MES
    -0.07
     sectors
    -0.07
    .flip
    -0.07
    ae
    -0.06
     Putin
    -0.06
    かり
    -0.06
     gap
    -0.06
    POSITIVE LOGITS
    وان
    0.06
    لمة
    0.06
    urum
    0.06
    ็ว
    0.06
    ньому
    0.06
    少し
    0.06
     ruce
    0.06
     outraged
    0.06
     beraber
    0.06
    таки
    0.06
    Act Density 0.040%

    No Known Activations