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

    Neuronpedia

    INDEX
    Explanations

    sighs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deleteAll
    0.46
     slow
    0.42
     wildly
    0.42
     siphon
    0.41
     Takashi
    0.41
     slowly
    0.40
    ில
    0.39
     savag
    0.39
     untold
    0.38
    泷
    0.38
    POSITIVE LOGITS
    重
    0.67
    heavy
    0.65
    Heavy
    0.64
     Heavy
    0.63
    重的
    0.62
     heavy
    0.61
     heaviest
    0.50
     schweren
    0.50
     trọng
    0.49
     heavyweight
    0.49
    Act Density 0.002%

    No Known Activations