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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    go
    -0.72
    á
    -0.69
     wikipagina
    -0.67
     métallique
    -0.67
     polaire
    -0.66
     fotografico
    -0.65
     brosse
    -0.64
     manteau
    -0.64
     Mexicana
    -0.64
     énergétique
    -0.62
    POSITIVE LOGITS
     autorytatywna
    0.57
    ↵↵
    0.54
     <=",
    0.54
    <bos>
    0.52
    ArgsConstructor
    0.52
    UrlResolution
    0.51
    PhysRevD
    0.51
    //
    0.51
    ="@+
    0.51
    .,
    0.50
    Act Density 0.373%

    No Known Activations