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
    /MM
    -0.07
     sharedInstance
    -0.07
    蕹
    -0.07
    キャ
    -0.07
    oklyn
    -0.07
     Españ
    -0.07
     overposting
    -0.07
     AnyObject
    -0.06
     כן
    -0.06
    钺
    -0.06
    POSITIVE LOGITS
     של
    0.07
    wid
    0.07
     resisting
    0.07
     ل
    0.06
    rio
    0.06
     lud
    0.06
    Country
    0.06
    -lib
    0.06
     để
    0.06
     gcc
    0.06
    Act Density 0.072%

    No Known Activations