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

    Neuronpedia

    INDEX
    Explanations

    honest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ця
    -0.07
    Await
    -0.07
     ziy
    -0.06
     út
    -0.06
    tram
    -0.06
    koa
    -0.06
    δει
    -0.06
     kesinlikle
    -0.06
    се
    -0.06
    牛
    -0.06
    POSITIVE LOGITS
    ':'
    0.08
    目前
    0.07
    ()),↵
    0.07
     dare
    0.06
     Romans
    0.06
     :-
    0.06
     Developer
    0.06
    ':
    0.06
     );
    0.06
    \Mail
    0.06
    Act Density 0.007%

    No Known Activations