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

    Neuronpedia

    INDEX
    Explanations

    universities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ion
    -0.07
    ,'%
    -0.07
     layers
    -0.06
    ＜
    -0.06
     cleanliness
    -0.06
     Bor
    -0.06
    .Txt
    -0.06
     tours
    -0.06
    Curso
    -0.06
    .txt
    -0.06
    POSITIVE LOGITS
     university
    0.12
     Universities
    0.11
     universities
    0.09
     uni
    0.08
    Uni
    0.08
     Üniversit
    0.07
     üniversit
    0.07
    (interval
    0.07
    iв
    0.06
    Connell
    0.06
    Act Density 0.012%

    No Known Activations