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

    Neuronpedia

    INDEX
    Explanations

    types and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clear
    0.63
     cloud
    0.62
     clouds
    0.62
     apparent
    0.61
     foundry
    0.58
     TM
    0.58
     ver
    0.58
     fraud
    0.57
     clean
    0.57
     handmade
    0.56
    POSITIVE LOGITS
        
    2.02
       
    1.86
         
    1.71
    1.42
          
    1.25
    <0xE3>
    1.18
           
    1.17
            
    1.14
      
    1.05
             
    0.99
    Act Density 0.684%

    No Known Activations