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

    Neuronpedia

    INDEX
    Explanations

    Court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BSITE
    -0.07
    azzi
    -0.07
    (coeff
    -0.07
    ptype
    -0.07
     SECTION
    -0.06
    ")]↵
    -0.06
    ší
    -0.06
    ystate
    -0.06
     Scroll
    -0.06
     landmark
    -0.06
    POSITIVE LOGITS
     McDonald
    0.07
     ShoppingCart
    0.07
    敗
    0.07
     Prosec
    0.06
     Mann
    0.06
     discrepancies
    0.06
    几乎
    0.06
    ышлен
    0.06
     quadrant
    0.06
     становится
    0.06
    Act Density 0.000%

    No Known Activations