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

    Neuronpedia

    INDEX
    Explanations

    description of quantity or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hyped
    1.11
     iteratively
    0.93
     dudes
    0.93
     ASAP
    0.93
     zoomed
    0.83
     Maybe
    0.82
     amps
    0.79
    強調
    0.79
    maybe
    0.79
     spandex
    0.78
    POSITIVE LOGITS
     trifle
    1.07
     remarkable
    1.07
     sufficiency
    1.04
     multitude
    0.95
     trifling
    0.95
     peculiar
    0.91
     dreadful
    0.91
     curious
    0.90
     thousand
    0.90
     prodigious
    0.89
    Act Density 0.086%

    No Known Activations