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

    Neuronpedia

    INDEX
    Explanations

    ways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     framework
    -0.08
     Framework
    -0.07
     sailors
    -0.07
     shady
    -0.07
     slav
    -0.06
     PURE
    -0.06
    елик
    -0.06
     моря
    -0.06
    .PL
    -0.06
    /dist
    -0.06
    POSITIVE LOGITS
    []={
    0.07
     carta
    0.07
    文章
    0.07
    .setOn
    0.06
     donors
    0.06
    سه
    0.06
    ultz
    0.06
     коштів
    0.06
     QR
    0.06
     UIAlertAction
    0.06
    Act Density 0.025%

    No Known Activations