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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \xff
    -0.08
    Preferred
    -0.07
     StObject
    -0.07
     dàng
    -0.07
    �
    -0.07
    トップ
    -0.07
     ebp
    -0.07
    绉
    -0.07
     fought
    -0.07
    storm
    -0.07
    POSITIVE LOGITS
    董
    0.08
    أخو
    0.08
     corner
    0.07
    <H
    0.07
    تقلي
    0.07
    side
    0.07
    왔
    0.07
     Chains
    0.07
     siècle
    0.06
    收回
    0.06
    Act Density 0.010%

    No Known Activations