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
    	HX
    -0.07
    Gs
    -0.07
     unnatural
    -0.06
    습니다
    -0.06
     STILL
    -0.06
    Passed
    -0.06
     Lexus
    -0.06
     TPP
    -0.06
    였다
    -0.06
     eksik
    -0.06
    POSITIVE LOGITS
    :↵↵↵↵↵↵
    0.07
    -cat
    0.07
    ustrial
    0.07
     желез
    0.06
    orama
    0.06
    ट
    0.06
     아버지
    0.06
    -era
    0.06
    .createServer
    0.06
     فایل
    0.06
    Act Density 0.041%

    No Known Activations