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

    Neuronpedia

    INDEX
    Explanations

    open-ended relative pronouns and words indicating uncertainty.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __':
    -0.62
     متعلقه
    -0.57
    __":
    -0.56
    (&:
    -0.54
    ioutil
    -0.53
     BufferedReader
    -0.52
    strconv
    -0.52
    RectangleBorder
    -0.52
    LikeLike
    -0.51
    LikeLiked
    -0.51
    POSITIVE LOGITS
    InitVars
    0.64
    Rohy
    0.57
    Personensuche
    0.57
     Paglinawan
    0.53
     autorytatywna
    0.52
     betweenstory
    0.52
    OuterClass
    0.52
    Karakteristik
    0.51
    tagHelperRunner
    0.50
     BoxDecoration
    0.50
    Act Density 3.018%

    No Known Activations