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

    Neuronpedia

    INDEX
    Explanations

    convolutional filters and channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     размеров
    0.45
    umu
    0.42
    icklabels
    0.39
    spatial
    0.39
    Dimension
    0.38
     astrocyte
    0.38
    resize
    0.38
    anatom
    0.38
     बोस
    0.38
     IP
    0.37
    POSITIVE LOGITS
     filters
    0.69
    Filters
    0.65
    フィルター
    0.65
     Filters
    0.63
    filters
    0.59
     filter
    0.58
     FILTER
    0.57
    FILTER
    0.56
     filtre
    0.54
     filtro
    0.54
    Act Density 0.022%

    No Known Activations