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

    Neuronpedia

    INDEX
    Explanations

    Yields, Prep time, Cook time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
          
    0.45
    ::
    0.45
    '
    0.41
    ’
    0.39
                        
    0.39
    -
    0.39
                    
    0.38
                       
    0.38
    ,
    0.38
     &
    0.37
    POSITIVE LOGITS
     Tamaño
    0.49
    ンドン
    0.44
     további
    0.41
    ٹرز
    0.40
     무게
    0.39
     üks
    0.39
    ක
    0.39
    TimeUnit
    0.38
    ꔹ
    0.38
    㑨
    0.38
    Act Density 0.023%

    No Known Activations