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

    Neuronpedia

    INDEX
    Explanations

    opinions and emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -is
    -0.07
    -Benz
    -0.07
    oo
    -0.07
     ani
    -0.07
    (show
    -0.06
     Mundo
    -0.06
    '(
    -0.06
    -a
    -0.06
     至
    -0.06
     Password
    -0.06
    POSITIVE LOGITS
     INTER
    0.06
     Career
    0.06
    .IsChecked
    0.06
    *);↵
    0.06
     cherish
    0.06
    armor
    0.06
    Footer
    0.06
    основ
    0.06
    (())↵
    0.06
     veri
    0.05
    Act Density 0.316%

    No Known Activations