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

    Neuronpedia

    INDEX
    Explanations

    caffe

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the deep-learning framework name “Caffe.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    267
    -0.07
    xFFFFFF
    -0.07
    257
    -0.06
    +r
    -0.06
     MK
    -0.06
    -real
    -0.06
    interpreter
    -0.06
    dál
    -0.06
    _res
    -0.06
     rider
    -0.06
    POSITIVE LOGITS
     caffe
    0.08
    caf
    0.08
     captive
    0.07
     percept
    0.07
     happy
    0.07
     temp
    0.07
     baz
    0.07
     kite
    0.07
     испыт
    0.07
    ulp
    0.07
    Act Density 0.001%

    No Known Activations