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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Чтобы
    -0.07
     lush
    -0.07
    )/
    -0.07
     integrates
    -0.06
    קשים
    -0.06
    ETweet
    -0.06
     获取
    -0.06
    ﱵ
    -0.06
    TreeView
    -0.06
    rgctx
    -0.06
    POSITIVE LOGITS
                            
↵
    0.08
                        ↵
    0.07
    .\
    0.07
    						↵
    0.07
            	↵
    0.07
     |↵
    0.07
     мар
    0.07
     المنزل
    0.07
    |↵
    0.07
    {
↵
    0.06
    Act Density 0.008%

    No Known Activations