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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愿
    -0.07
    ьому
    -0.07
    相信
    -0.07
    operators
    -0.06
    war
    -0.06
     facilities
    -0.06
     carriers
    -0.06
     cả
    -0.06
     Charges
    -0.06
    ariate
    -0.06
    POSITIVE LOGITS
     Eg
    0.06
    })();↵↵
    0.06
     lithium
    0.06
    ظام
    0.06
     audi
    0.06
    >All
    0.06
     Anton
    0.06
    });↵↵↵↵
    0.06
    ��取
    0.06
     Rath
    0.05
    Act Density 0.006%

    No Known Activations