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

    Neuronpedia

    INDEX
    Explanations

    fourth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aland
    -0.07
    <>(
    -0.07
     رب
    -0.06
     село
    -0.06
     useRef
    -0.06
    uncia
    -0.06
     Mellon
    -0.06
     lis
    -0.06
    εν
    -0.05
     kü
    -0.05
    POSITIVE LOGITS
    اضي
    0.07
    FT
    0.07
    585
    0.07
    γωγή
    0.07
     FT
    0.06
     ShoppingCart
    0.06
     policies
    0.06
     тон
    0.06
    $file
    0.06
    _preference
    0.06
    Act Density 0.001%

    No Known Activations