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

    Neuronpedia

    INDEX
    Explanations

    activation functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    223
    -0.07
     cram
    -0.07
    'RE
    -0.07
    .Video
    -0.07
    -images
    -0.06
     Become
    -0.06
     SwiftUI
    -0.06
    组
    -0.06
     Part
    -0.06
     existe
    -0.06
    POSITIVE LOGITS
    sigmoid
    0.12
    softmax
    0.09
    .sigmoid
    0.08
     softmax
    0.08
     sigmoid
    0.08
    igmoid
    0.08
    frican
    0.07
    Lisa
    0.07
    	code
    0.07
    May
    0.06
    Act Density 0.001%

    No Known Activations