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

    Neuronpedia

    INDEX
    Explanations

    economics, employment data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    هاي
    -0.08
     threats
    -0.08
     oriental
    -0.08
     themes
    -0.07
     potenci
    -0.07
     problems
    -0.07
    bad
    -0.07
    主题
    -0.07
     rač
    -0.07
     drugs
    -0.07
    POSITIVE LOGITS
    _CREATE
    0.08
     Fø
    0.08
     Diaries
    0.08
     Führ
    0.08
     kön
    0.08
     supplément
    0.08
     welfare
    0.08
     Haut
    0.07
     barr
    0.07
    Filesystem
    0.07
    Act Density 0.001%

    No Known Activations