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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cout
    -0.08
     diễn
    -0.08
    西宁
    -0.07
     Helmet
    -0.07
     vib
    -0.07
    볐
    -0.07
    ជ
    -0.07
     surfaced
    -0.07
     NASCAR
    -0.07
     каж
    -0.07
    POSITIVE LOGITS
    .EventArgs
    0.08
    انا
    0.08
    "}>↵
    0.07
     antagon
    0.07
    phans
    0.07
    	s
    0.07
    Mode
    0.07
    事务
    0.07
    vars
    0.07
    贪
    0.07
    Act Density 0.024%

    No Known Activations