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

    Neuronpedia

    INDEX
    Explanations

    Rectangular/angular shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    483
    -0.07
    .cluster
    -0.06
     Με
    -0.06
     trolls
    -0.06
     People
    -0.06
     healthcare
    -0.06
     part
    -0.06
    %
    -0.06
    пе
    -0.06
    -post
    -0.06
    POSITIVE LOGITS
    iform
    0.07
     Zuckerberg
    0.06
    оров
    0.06
    (setting
    0.06
     triangular
    0.06
     маль
    0.06
     omp
    0.06
     зави
    0.06
     conhe
    0.06
    rů
    0.06
    Act Density 0.013%

    No Known Activations