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

    Neuronpedia

    INDEX
    Explanations

    "so far, so good"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Or
    -0.08
     bewust
    -0.08
     conséquent
    -0.07
    annis
    -0.07
    者
    -0.07
    shi
    -0.07
     nearly
    -0.07
     noz
    -0.07
     contracting
    -0.07
    elli
    -0.07
    POSITIVE LOGITS
    ↵		
↵
    0.10
    	
↵	
↵
    0.09
    	
↵
↵
    0.09
    ↵		↵
    0.09
    ↵	
↵
    0.08
    	
↵
    0.08
    ичным
    0.08
    	↵		↵
    0.08
     iria
    0.08
    	Table
    0.08
    Act Density 0.022%

    No Known Activations