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

    Neuronpedia

    INDEX
    Explanations

    notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SQLITE
    -0.09
     maß
    -0.08
    эра
    -0.08
    ुल्क
    -0.08
     steep
    -0.08
    utung
    -0.07
     leukemia
    -0.07
    ileno
    -0.07
    olicy
    -0.07
     заключается
    -0.07
    POSITIVE LOGITS
     inconsist
    0.09
     imperfections
    0.08
     occasionally
    0.08
     inse
    0.07
     affectionate
    0.07
     табиғ
    0.07
     palavras
    0.07
    .*;↵↵/
    0.07
     الطبيعي
    0.07
    'étais
    0.07
    Act Density 0.000%

    No Known Activations