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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _notification
    -0.07
    wards
    -0.07
    bounds
    -0.07
     لإ
    -0.07
     Street
    -0.06
    уватися
    -0.06
    Override
    -0.06
     İb
    -0.06
     Lawrence
    -0.06
    InInspector
    -0.06
    POSITIVE LOGITS
     acclaimed
    0.07
    ilitating
    0.07
    ولی
    0.06
     SUCH
    0.06
    illac
    0.06
    /am
    0.06
    ension
    0.06
    Initializer
    0.06
    .static
    0.06
     مخروط
    0.06
    Act Density 0.011%

    No Known Activations