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

    Neuronpedia

    INDEX
    Explanations

    important

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oa
    -0.07
    (mt
    -0.07
     playoffs
    -0.06
    weather
    -0.06
    .addActionListener
    -0.06
    .do
    -0.06
    _http
    -0.06
     zf
    -0.06
     velocities
    -0.06
    _now
    -0.06
    POSITIVE LOGITS
    Türk
    0.07
    �
    0.07
    кус
    0.07
    .viewModel
    0.07
     Türk
    0.07
    告
    0.07
    RootElement
    0.07
    Pros
    0.06
    Bug
    0.06
     зави
    0.06
    Act Density 0.015%

    No Known Activations