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

    Neuronpedia

    INDEX
    Explanations

    Circuit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سام
    -0.06
     orbital
    -0.06
     principalTable
    -0.06
     شار
    -0.06
    طال
    -0.06
     Ruth
    -0.06
    Doctors
    -0.06
     Nas
    -0.06
     výro
    -0.06
     presidents
    -0.06
    POSITIVE LOGITS
    ايد
    0.07
     [↵
    0.07
    auction
    0.06
    .gson
    0.06
    .spy
    0.06
    Series
    0.06
    '))
↵
    0.06
     Causes
    0.06
    {-
    0.06
     alertController
    0.06
    Act Density 0.013%

    No Known Activations