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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation or end of line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ังสือ
    0.31
    OLINA
    0.27
    макраты
    0.27
    鳧
    0.27
    بعة
    0.27
     defences
    0.27
    プレミア
    0.27
     tumours
    0.27
    Aldrich
    0.27
     gentamicin
    0.27
    POSITIVE LOGITS
    ↵↵
    0.44
          
    0.39
    ...
    0.38
        
    0.37
    ↵↵↵↵
    0.37
    q
    0.35
                    
    0.34
            
    0.33
    :
    0.33
    un
    0.33
    Act Density 0.008%

    No Known Activations