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

    Neuronpedia

    INDEX
    Explanations

    code operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ющ
    -0.08
    .Expect
    -0.07
    -wsj
    -0.07
     nave
    -0.06
     &_
    -0.06
    Con
    -0.06
    parts
    -0.06
    recated
    -0.06
    _greater
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     LAND
    0.07
    нения
    0.07
    нение
    0.06
     Nutrition
    0.06
     foods
    0.06
     Rena
    0.06
     thí
    0.06
     HE
    0.06
    ische
    0.06
    !(
    0.06
    Act Density 0.048%

    No Known Activations