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

    Neuronpedia

    INDEX
    Explanations

    Server management features/exporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Plane
    -0.09
    Autos
    -0.08
    Unit
    -0.08
    Oil
    -0.08
    (des
    -0.08
    bb
    -0.08
    omed
    -0.07
    Util
    -0.07
    aten
    -0.07
    allback
    -0.07
    POSITIVE LOGITS
     Brands
    0.09
     constantly
    0.08
     voortdurend
    0.08
     Editions
    0.08
     Verd
    0.08
     vär
    0.08
     sama
    0.08
     Marriott
    0.08
     frågor
    0.08
     ständig
    0.08
    Act Density 0.000%

    No Known Activations