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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /security
    -0.07
    .sg
    -0.06
     imperialism
    -0.06
     analytics
    -0.06
     мови
    -0.06
    /MM
    -0.06
    átis
    -0.06
    ▏▏
    -0.06
     Liber
    -0.06
    енного
    -0.06
    POSITIVE LOGITS
    Else
    0.06
     khỏ
    0.06
    물
    0.06
    -import
    0.06
    classified
    0.06
     Drink
    0.06
    NavLink
    0.06
    _now
    0.06
    ايات
    0.06
     itemprop
    0.06
    Act Density 0.008%

    No Known Activations