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

    Neuronpedia

    INDEX
    Explanations

    political commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     odd
    -0.07
    图书
    -0.07
     organ
    -0.07
    .Field
    -0.07
    集体
    -0.07
    	mysql
    -0.07
     infer
    -0.07
     instruction
    -0.06
    。↵↵↵↵
    -0.06
    〴
    -0.06
    POSITIVE LOGITS
    apk
    0.08
    atism
    0.07
     básica
    0.07
    清代
    0.07
     getUserId
    0.07
     countered
    0.07
    corev
    0.07
    ateau
    0.07
    .Utility
    0.07
     Rus
    0.07
    Act Density 0.200%

    No Known Activations