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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    结束
    -0.07
     Zend
    -0.07
    .fac
    -0.07
    늄
    -0.07
    ,right
    -0.06
     strr
    -0.06
     Nose
    -0.06
     Laz
    -0.06
    也开始
    -0.06
    ической
    -0.06
    POSITIVE LOGITS
    bucket
    0.08
     וב
    0.08
    ])]↵
    0.07
     ו
    0.07
    		
↵		
↵
    0.07
    infer
    0.07
     ","↵
    0.07
    ]][
    0.06
     đồng
    0.06
    끼
    0.06
    Act Density 0.254%

    No Known Activations