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

    Neuronpedia

    INDEX
    Explanations

    Asking about favorites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workforce
    -0.09
     Workforce
    -0.08
     обеспечить
    -0.08
     Accountant
    -0.08
    NAV
    -0.08
     Asa
    -0.07
    ാക്കി
    -0.07
     административ
    -0.07
    Arrange
    -0.07
     Arrange
    -0.07
    POSITIVE LOGITS
     preferencias
    0.16
     preferences
    0.16
    .favorite
    0.15
    favorite
    0.15
    Favorite
    0.14
     Lieblings
    0.14
    喜欢
    0.13
     favoriete
    0.13
     favorites
    0.13
     Preferences
    0.13
    Act Density 0.104%

    No Known Activations