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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “data.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rus
    -0.08
     tratamiento
    -0.07
     электри
    -0.07
    pring
    -0.07
     μπ
    -0.07
    .Paths
    -0.06
     будто
    -0.06
    .Class
    -0.06
    \Action
    -0.06
     элек
    -0.06
    POSITIVE LOGITS
     data
    0.10
     Data
    0.07
     DATA
    0.07
     historical
    0.07
     Dean
    0.06
     cán
    0.06
     deux
    0.06
     statistics
    0.06
    NX
    0.06
     dung
    0.06
    Act Density 0.034%

    No Known Activations