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

    Neuronpedia

    INDEX
    Explanations

    importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.64
    XmlAccessorType
    -0.64
     مشين
    -0.62
     defaultstate
    -0.58
    شهاد
    -0.57
     AssemblyCulture
    -0.57
    PagerAdapter
    -0.54
    ReusableCell
    -0.51
    حوالہ
    -0.51
    存于互联网档案馆
    -0.51
    POSITIVE LOGITS
    Задачи
    0.59
    0.58
    intă
    0.57
     sign
    0.56
    atecas
    0.53
     strategy
    0.52
     stratégie
    0.52
    #
    0.52
    excellents
    0.51
    marvin
    0.51
    Act Density 0.003%

    No Known Activations