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

    Neuronpedia

    INDEX
    Explanations

    filtering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ഏറ്റ
    -0.08
     гг
    -0.08
     خا
    -0.08
     rated
    -0.08
    .naming
    -0.08
    <footer
    -0.08
     composição
    -0.08
     modele
    -0.08
    ంప
    -0.07
     kasa
    -0.07
    POSITIVE LOGITS
    filter
    0.10
    .Filter
    0.10
    _filter
    0.10
    -filter
    0.09
    FILTER
    0.09
    _FILTER
    0.09
    Filter
    0.09
    _Filter
    0.09
     FILTER
    0.09
    .Sort
    0.09
    Act Density 0.004%

    No Known Activations