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

    Neuronpedia

    INDEX
    Explanations

    convolution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _infos
    -0.08
     arc
    -0.08
     retire
    -0.08
     subtitle
    -0.08
     lifelong
    -0.07
    Infos
    -0.07
     tink
    -0.07
     устройства
    -0.07
     portail
    -0.07
     year
    -0.07
    POSITIVE LOGITS
     convolution
    0.13
     stencil
    0.11
     receptive
    0.11
    _kernel
    0.10
     CNN
    0.10
     convol
    0.09
     sinc
    0.09
    _fft
    0.09
     peanut
    0.09
     peaked
    0.08
    Act Density 0.010%

    No Known Activations