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

    Neuronpedia

    INDEX
    Explanations

    matrix

    np_max-act · gemini-2.0-flash

    The neuron reliably flags occurrences of the term “matrix” in technical or scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Sale
    -0.06
    iyorlar
    -0.06
    قف
    -0.06
    (b
    -0.06
     ble
    -0.06
     고개를
    -0.06
    .VAL
    -0.06
    üslü
    -0.06
     робот
    -0.06
    (lbl
    -0.06
    POSITIVE LOGITS
     MATRIX
    0.08
     matrix
    0.08
     patriarch
    0.07
    _cats
    0.07
     Matrix
    0.07
     mtx
    0.07
    ={}
    0.07
    west
    0.07
     macros
    0.06
    tons
    0.06
    Act Density 0.003%

    No Known Activations