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

    Neuronpedia

    INDEX
    Explanations

    quantity words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.49
    :
    0.43
    4
    0.41
    8
    0.39
    *
    0.36
    7
    0.36
    ;
    0.35
    मो
    0.34
    Â
    0.34
    9
    0.34
    POSITIVE LOGITS
     dólares
    0.42
    eggs
    0.42
     átomos
    0.40
     oiseaux
    0.39
    aż
    0.39
    ্বস্ত
    0.39
     qualche
    0.38
     സു
    0.38
     JANUARY
    0.38
     équipe
    0.37
    Act Density 0.120%

    No Known Activations