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

    Neuronpedia

    INDEX
    Explanations

    Code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ữa
    -0.07
     اختيار
    -0.07
    מסעדה
    -0.07
     instanceof
    -0.07
     Dự
    -0.07
     помощью
    -0.06
     Garrett
    -0.06
    (lp
    -0.06
    ifications
    -0.06
    uale
    -0.06
    POSITIVE LOGITS
    zyst
    0.08
    WISE
    0.08
    体
    0.07
    .UP
    0.07
    blank
    0.07
    //=
    0.07
    MATRIX
    0.07
     contributing
    0.07
    sup
    0.07
     hemos
    0.07
    Act Density 0.016%

    No Known Activations