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

    Neuronpedia

    INDEX
    Explanations

    numeric indicators or values in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -1.08
    хьтан
    -1.06
     Paglinawan
    -1.05
     pylint
    -1.02
    NUMX
    -0.95
     autorytatywna
    -0.95
    PhysRevD
    -0.93
     RoutedEventArgs
    -0.92
    PhysRevLett
    -0.92
    WriteTagHelper
    -0.89
    POSITIVE LOGITS
    ↵
    1.41
      
    1.16
    ↵↵
    1.16
    1.15
       
    1.05
    ↵↵↵
    0.93
         
    0.91
        
    0.90
    	
    0.88
    </h3>
    0.87
    Act Density 0.046%
    No Known Activations