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
    -threatening
    -0.10
    -threat
    -0.09
    -angle
    -0.09
     discomfort
    -0.09
    Russ
    -0.09
    центр
    -0.08
    _angle
    -0.08
     classroom
    -0.08
    ১৭
    -0.08
     looming
    -0.08
    POSITIVE LOGITS
     convolution
    0.19
     convol
    0.15
     Fourier
    0.10
     fft
    0.09
     kernel
    0.09
    卷
    0.09
     lodash
    0.09
     Albums
    0.09
     Toe
    0.09
     kernels
    0.09
    Act Density 0.013%

    No Known Activations