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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Then
    -0.07
     Airport
    -0.07
    包
    -0.07
    Country
    -0.07
     distr
    -0.07
     لإ
    -0.07
    predictions
    -0.06
    (newValue
    -0.06
    urchases
    -0.06
    deviceId
    -0.06
    POSITIVE LOGITS
     haute
    0.08
     Sandy
    0.06
    ؤ
    0.06
    frau
    0.06
    alli
    0.06
    QS
    0.06
    .Criteria
    0.06
    عا
    0.06
     وقد
    0.06
     CST
    0.06
    Act Density 0.023%

    No Known Activations