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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rigorous
    -0.07
    σεων
    -0.07
    178
    -0.07
    _.
    -0.06
     tut
    -0.06
    기준
    -0.06
    ’daki
    -0.06
     defeat
    -0.06
    (cond
    -0.06
    енными
    -0.06
    POSITIVE LOGITS
     misc
    0.07
     plugs
    0.06
     backend
    0.06
    istingu
    0.06
    populate
    0.06
    "data
    0.06
    ++){
↵
    0.06
    ))
↵
    0.06
    -->
↵
    0.06
     représent
    0.06
    Act Density 0.018%

    No Known Activations