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

    Neuronpedia

    INDEX
    Explanations

    action or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بتساوي
    0.35
     جوړونک
    0.34
    LastGen
    0.34
     الاعدادي
    0.33
     ईमित्र
    0.33
    respArray
    0.33
    getBlueTeam
    0.33
    اونلو
    0.33
    linkOpacity
    0.32
    ल्लाला
    0.32
    POSITIVE LOGITS
      
    0.44
    0.43
    ↵↵
    0.39
          
    0.38
              
    0.38
        
    0.37
       
    0.35
            
    0.35
    ,
    0.35
    1
    0.35
    Act Density 0.756%

    No Known Activations