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

    Neuronpedia

    INDEX
    Explanations

    Nonsensical/gibberish text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     results
    -0.06
    acy
    -0.06
    bi
    -0.06
    IRR
    -0.06
     صورت
    -0.06
     Stevens
    -0.06
    ेश
    -0.06
    altar
    -0.06
     deals
    -0.06
     Hà
    -0.06
    POSITIVE LOGITS
     thoại
    0.07
    　 　 　 　 　
    0.07
    (xy
    0.06
    ","");↵
    0.06
     ftp
    0.06
     英语
    0.06
    ในป
    0.06
    _bs
    0.06
    -с
    0.06
    แฟ
    0.06
    Act Density 0.047%

    No Known Activations