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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	describe
    -0.07
    sse
    -0.07
    (WebDriver
    -0.06
    的笑容
    -0.06
    Almost
    -0.06
    本网
    -0.06
     imperative
    -0.06
    ｻ
    -0.06
     Torrent
    -0.06
     sniper
    -0.06
    POSITIVE LOGITS
     Hogwarts
    0.08
    𓈒
    0.07
    芊
    0.07
    OKIE
    0.07
    峧
    0.07
     kişiler
    0.07
     cocos
    0.07
     arkadaş
    0.07
    (_("
    0.07
    apellido
    0.07
    Act Density 0.006%

    No Known Activations