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

    Neuronpedia

    INDEX
    Explanations

    gibberish and potentially foreign words related to religion and folklore

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.51
    RectangleBorder
    -0.44
    DoubleQuotes
    -0.41
    AddTagHelper
    -0.38
     AssemblyProduct
    -0.37
     BoxDecoration
    -0.35
    GEBURTSDATUM
    -0.34
    ָד
    -0.34
     Monfieur
    -0.33
    ByVersion
    -0.33
    POSITIVE LOGITS
    )=>{
    0.52
     n
    0.49
     kh
    0.49
    -]
    0.48
    ništ
    0.48
     khe
    0.48
     t
    0.47
    ("]");
    0.47
     r
    0.47
    ]+=
    0.47
    Act Density 17.559%

    No Known Activations