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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atra
    -0.07
     Dod
    -0.06
     pedigree
    -0.06
    .eng
    -0.06
     �
    -0.06
     오후
    -0.06
    .after
    -0.06
    .cid
    -0.06
    rq
    -0.06
     HERO
    -0.06
    POSITIVE LOGITS
    \",↵
    0.08
     슬
    0.08
    ])),↵
    0.07
     unrestricted
    0.06
    역
    0.06
    	System
    0.06
     spokesman
    0.06
    啦
    0.06
     },↵
    0.06
     zwischen
    0.06
    Act Density 0.003%

    No Known Activations