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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stanford
    -0.07
     DAC
    -0.07
    اید
    -0.07
    zu
    -0.07
    ////
    -0.06
    燕
    -0.06
    778
    -0.06
    хо
    -0.06
    erseniz
    -0.06
    ивается
    -0.06
    POSITIVE LOGITS
    職
    0.07
    checksum
    0.06
    tro
    0.06
     hely
    0.06
    FXML
    0.06
    TIME
    0.06
    .twitter
    0.06
     sớm
    0.06
    civil
    0.06
    @Component
    0.06
    Act Density 0.034%

    No Known Activations