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

    Neuronpedia

    INDEX
    Explanations

    Code and diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rutin
    -0.08
    324
    -0.08
    IFI
    -0.08
    txt
    -0.07
    Taxes
    -0.07
     메뉴
    -0.07
     Personally
    -0.07
    预算
    -0.07
     repert
    -0.07
    -sex
    -0.07
    POSITIVE LOGITS
            
    0.10
    ↓↵↵
    0.10
        
    0.10
     
    0.10
      
    0.10
       
    0.10
    ┃
    0.09
     �
    0.09
    0.09
    0.09
    Act Density 0.022%

    No Known Activations