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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vistas
    -0.07
     deferred
    -0.07
    ortex
    -0.07
     corre
    -0.06
    symbols
    -0.06
    formed
    -0.06
    advertisement
    -0.06
    ersh
    -0.06
    пор
    -0.06
    Career
    -0.06
    POSITIVE LOGITS
    .ListBox
    0.07
    NAMESPACE
    0.07
     거래
    0.07
     欧
    0.06
    PLIER
    0.06
    .InnerException
    0.06
     겁
    0.06
    мерикан
    0.06
     Freel
    0.06
     overload
    0.05
    Act Density 0.002%

    No Known Activations