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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هواپیم
    -0.07
    -haspopup
    -0.07
    VICES
    -0.07
     Unauthorized
    -0.07
    Chan
    -0.06
    -res
    -0.06
     Н
    -0.06
    hawks
    -0.06
     InterruptedException
    -0.06
    ivan
    -0.06
    POSITIVE LOGITS
     =
    0.08
     warriors
    0.07
    ادة
    0.07
    ايش
    0.07
     التف
    0.06
     umož
    0.06
     Д
    0.06
     پزش
    0.06
    eming
    0.06
    .models
    0.06
    Act Density 0.011%

    No Known Activations