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

    Neuronpedia

    INDEX
    Explanations

    National

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imation
    -0.07
     yanı
    -0.07
     disconnect
    -0.07
    -form
    -0.06
     penetr
    -0.06
     stand
    -0.06
    Witness
    -0.06
     Disconnect
    -0.06
    خة
    -0.06
     button
    -0.06
    POSITIVE LOGITS
    ,False
    0.06
     StatefulWidget
    0.06
     ніколи
    0.06
    >/
    0.06
    实验
    0.06
     incompetence
    0.06
    ,True
    0.06
     seri
    0.06
    _AI
    0.06
    분석
    0.06
    Act Density 0.003%

    No Known Activations