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

    Neuronpedia

    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achers
    -0.07
    Notifications
    -0.07
     Andy
    -0.07
    rooms
    -0.07
     regression
    -0.07
    Edited
    -0.06
     prosecutors
    -0.06
    licants
    -0.06
    但
    -0.06
    xA
    -0.06
    POSITIVE LOGITS
     sữa
    0.07
    _configure
    0.06
     εμπ
    0.06
     배
    0.06
    (est
    0.06
    务
    0.06
    @FXML
    0.06
    .lat
    0.06
    ЎыџN
    0.06
    eatures
    0.06
    Act Density 0.038%

    No Known Activations