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

    Neuronpedia

    INDEX
    Explanations

    minimum possible score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ividual
    0.72
    AVOA
    0.72
     micelles
    0.71
    icional
    0.71
    ósticos
    0.71
     cultivation
    0.69
    gebras
    0.69
    iculares
    0.69
     அளவு
    0.68
     piqu
    0.68
    POSITIVE LOGITS
          
    0.65
         
    0.64
             
    0.60
    arschijnlijk
    0.58
       
    0.58
     cruel
    0.55
        
    0.54
            
    0.54
                  
    0.54
              
    0.54
    Act Density 0.001%

    No Known Activations