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

    Neuronpedia

    INDEX
    Explanations

    basal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     робот
    -0.07
    	dist
    -0.06
    شد
    -0.06
     sửa
    -0.06
     surfaced
    -0.06
    lab
    -0.06
     alleviate
    -0.06
    -max
    -0.06
    儀
    -0.06
    my
    -0.06
    POSITIVE LOGITS
    (handle
    0.07
    _finalize
    0.07
    .Throw
    0.07
     QFile
    0.06
    GMEM
    0.06
     saison
    0.06
     dataTable
    0.06
    (IO
    0.06
    )dealloc
    0.06
    (Environment
    0.06
    Act Density 0.002%

    No Known Activations