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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     billeder
    -0.06
    hay
    -0.06
    faces
    -0.06
     ориг
    -0.06
     LinearLayout
    -0.06
    .vertical
    -0.06
    ipation
    -0.06
    仰
    -0.06
     pornô
    -0.05
    POSITIVE LOGITS
    では
    0.08
     Products
    0.07
     amort
    0.07
     ‎
    0.07
    --
    0.06
    .Put
    0.06
    ंघ
    0.06
    /J
    0.06
     persuaded
    0.06
     Giants
    0.06
    Act Density 0.002%

    No Known Activations