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

    Neuronpedia

    INDEX
    Explanations

    reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     те
    -0.07
     Eggs
    -0.07
    odcast
    -0.06
     چاپ
    -0.06
     bizi
    -0.06
     lleg
    -0.06
    甚
    -0.06
     giành
    -0.06
     även
    -0.06
     желуд
    -0.06
    POSITIVE LOGITS
     report
    0.07
    ederal
    0.06
    /pol
    0.06
    .Fail
    0.06
     chin
    0.06
     Profile
    0.06
     DataType
    0.06
    ========
    0.06
     corporate
    0.06
    .slim
    0.06
    Act Density 0.004%

    No Known Activations