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

    Neuronpedia

    INDEX
    Explanations

    Chess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conveniently
    -0.07
     disposable
    -0.07
    霸气
    -0.06
    	full
    -0.06
     bề
    -0.06
     Om
    -0.06
     kisses
    -0.06
    😏
    -0.06
    同步
    -0.06
     Describe
    -0.06
    POSITIVE LOGITS
    GetWidth
    0.07
    먀
    0.07
    臟
    0.07
    保持
    0.07
     marc
    0.07
    ﻬ
    0.07
    解决
    0.07
     noticing
    0.07
    gło
    0.06
    YZ
    0.06
    Act Density 0.022%

    No Known Activations