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
     boxShadow
    -0.07
    ира
    -0.06
     Dress
    -0.06
    朝
    -0.06
    ریف
    -0.06
    ══
    -0.06
    観
    -0.06
     zwei
    -0.06
     roam
    -0.06
    achie
    -0.06
    POSITIVE LOGITS
     impactful
    0.06
    unwrap
    0.06
    Cog
    0.06
    /models
    0.06
    国
    0.06
     settlers
    0.06
     termination
    0.06
    		
↵
↵
    0.06
    ')");↵
    0.06
     Invalid
    0.06
    Act Density 0.002%

    No Known Activations