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

    Neuronpedia

    INDEX
    Explanations

    statistical analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _connection
    -0.07
     losers
    -0.07
     strictly
    -0.07
     Equals
    -0.06
    ляем
    -0.06
    -pound
    -0.06
    rectangle
    -0.06
    .bottom
    -0.06
     mob
    -0.06
    gif
    -0.06
    POSITIVE LOGITS
    lock
    0.07
     مج
    0.07
     telemetry
    0.06
    иной
    0.06
    LOCK
    0.06
    window
    0.06
    .views
    0.06
    .appcompat
    0.06
    Trail
    0.06
     витами
    0.06
    Act Density 0.050%

    No Known Activations