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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Mahar
    -0.06
     Huss
    -0.06
    .histogram
    -0.06
    小学
    -0.06
     Bruce
    -0.06
    XB
    -0.06
     Santos
    -0.06
    Europe
    -0.06
     testers
    -0.06
    POSITIVE LOGITS
     contempor
    0.07
     россий
    0.07
    Estimated
    0.07
     contained
    0.06
    無し
    0.06
    ież
    0.06
     значительно
    0.06
    または
    0.06
                      ↵
    0.06
    dění
    0.06
    Act Density 0.003%

    No Known Activations