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

    Neuronpedia

    INDEX
    Explanations

    transpose

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “transpose,” especially in the context of matrix transposition.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     filthy
    -0.07
     dalla
    -0.07
     buckets
    -0.07
     Buck
    -0.07
     ارزیابی
    -0.06
    _ll
    -0.06
    iping
    -0.06
     Shelter
    -0.06
    <byte
    -0.06
     balık
    -0.06
    POSITIVE LOGITS
     transpose
    0.09
    _Dep
    0.07
     �
    0.07
    Transpose
    0.07
     Пос
    0.07
     unused
    0.06
    Προ
    0.06
    另外
    0.06
     понад
    0.06
    _Pro
    0.06
    Act Density 0.002%

    No Known Activations