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

    Neuronpedia

    INDEX
    Explanations

    below

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.63
     femininas
    -0.60
     RoutedEventArgs
    -0.56
    ագրություններ
    -0.53
    orszá
    -0.51
     abaixo
    -0.50
     >=",
    -0.50
     veau
    -0.47
    documentclass
    -0.47
     خارجية
    -0.46
    POSITIVE LOGITS
    ConstraintMaker
    0.74
    exitRule
    0.73
    jaer
    0.65
     resourceCulture
    0.61
    protoc
    0.60
     Biôgrafia
    0.54
    Попис
    0.53
    userdetails
    0.51
     tội
    0.51
     Indonesia
    0.50
    Act Density 0.051%

    No Known Activations