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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foreground
    -0.07
    _nb
    -0.07
     cabinets
    -0.07
     Makeup
    -0.07
    found
    -0.07
     True
    -0.06
     Options
    -0.06
     preamble
    -0.06
     Advocate
    -0.06
    _third
    -0.06
    POSITIVE LOGITS
    鲔
    0.08
     bli
    0.07
    保护区
    0.07
    lararası
    0.07
    哒
    0.07
    登录
    0.07
    انتشار
    0.07
    片区
    0.07
    laştır
    0.07
    -hash
    0.07
    Act Density 0.006%

    No Known Activations