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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @app
    -0.06
    fs
    -0.06
    (att
    -0.06
    pis
    -0.06
    .SpringBootTest
    -0.06
     competitions
    -0.06
    Monitoring
    -0.05
     online
    -0.05
    .Layer
    -0.05
    .material
    -0.05
    POSITIVE LOGITS
    ("("
    0.07
    िवर
    0.07
    igration
    0.06
    icaid
    0.06
    电视
    0.06
     instructed
    0.06
    饭
    0.06
    [Byte
    0.06
    AuthToken
    0.06
     congestion
    0.06
    Act Density 0.004%

    No Known Activations