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

    Neuronpedia

    INDEX
    Explanations

    CNN architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multidisciplinary
    -0.08
     bổ
    -0.08
     mechanic
    -0.08
     secular
    -0.08
     deco
    -0.07
     igual
    -0.07
    latex
    -0.07
    Ranges
    -0.07
     ranged
    -0.07
     supernatural
    -0.07
    POSITIVE LOGITS
     pretrained
    0.10
    (img
    0.09
     imagen
    0.09
     CNN
    0.09
     Retina
    0.09
    CNN
    0.09
    Imagen
    0.08
     backbone
    0.08
    imagen
    0.08
     Sime
    0.08
    Act Density 0.008%

    No Known Activations