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

    Neuronpedia

    INDEX
    Explanations

    specific terms after 'the'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.67
    !
    0.66
     ofthe
    0.66
    The
    0.64
    [/
    0.62
     Ultimately
    0.61
    Ultimately
    0.61
    ：（
    0.60
     โดย
    0.59
    <eos>
    0.59
    POSITIVE LOGITS
     coefficients
    1.17
     others
    1.01
     coefficient
    0.98
     parameters
    0.92
     values
    0.91
     ones
    0.90
     criteria
    0.90
     subtypes
    0.88
     sects
    0.87
     proportions
    0.86
    Act Density 0.096%

    No Known Activations