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

    Neuronpedia

    INDEX
    Explanations

    class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NAM
    0.42
    execute
    0.41
    unexpected
    0.37
     swearing
    0.37
    execution
    0.37
    inator
    0.37
    kne
    0.37
    entwicklung
    0.36
    NBA
    0.36
     complement
    0.36
    POSITIVE LOGITS
     class
    0.44
     classe
    0.43
     শ্রেণির
    0.42
     kelas
    0.41
     Klasse
    0.40
     stacks
    0.39
     کلاس
    0.38
     класу
    0.38
    മൂഹ
    0.38
    class
    0.38
    Act Density 0.000%

    No Known Activations