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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (BASE
    -0.07
     Twig
    -0.06
    _epochs
    -0.06
     associate
    -0.06
    /react
    -0.06
    lek
    -0.06
     coco
    -0.06
    GER
    -0.06
    itude
    -0.06
    \Helper
    -0.06
    POSITIVE LOGITS
     ایست
    0.06
    (vo
    0.06
    	Buffer
    0.06
    inctions
    0.06
     truncate
    0.06
    .loading
    0.06
     coff
    0.06
    这种
    0.06
     JOIN
    0.06
     Trash
    0.06
    Act Density 0.063%

    No Known Activations