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

    Neuronpedia

    INDEX
    Explanations

    conv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ster
    -0.07
     Lager
    -0.07
     данны
    -0.07
     Rice
    -0.06
    ere
    -0.06
    电影
    -0.06
     возду
    -0.06
    .imread
    -0.06
     ster
    -0.06
     aides
    -0.06
    POSITIVE LOGITS
     conv
    0.15
     Conv
    0.14
    conv
    0.13
    Conv
    0.12
     convo
    0.10
     convoy
    0.10
    (conv
    0.10
     convex
    0.09
     conven
    0.08
    (Conv
    0.08
    Act Density 0.008%

    No Known Activations