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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dup
    -0.07
     Plus
    -0.07
    box
    -0.07
     Pháp
    -0.06
    -0.06
     midd
    -0.06
     Pied
    -0.06
    牛
    -0.06
    App
    -0.06
     پاد
    -0.06
    POSITIVE LOGITS
     discovering
    0.07
     وكان
    0.07
    orne
    0.07
    ItemSelectedListener
    0.06
    oğun
    0.06
    χεία
    0.06
     freopen
    0.06
     STUD
    0.06
    (stderr
    0.06
     uyar
    0.06
    Act Density 0.008%
    No Known Activations