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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depict
    -0.07
    ';
    -0.07
    ğmen
    -0.06
     ais
    -0.06
     Lobby
    -0.06
     w
    -0.06
    (resources
    -0.06
     judges
    -0.06
     马
    -0.06
     seem
    -0.06
    POSITIVE LOGITS
    ाहत
    0.07
     zeros
    0.07
     застав
    0.07
     inev
    0.06
     cumpl
    0.06
    是一个
    0.06
     paar
    0.06
    cum
    0.06
     nevy
    0.06
     CGFloat
    0.06
    Act Density 0.026%

    No Known Activations