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

    Neuronpedia

    INDEX
    Explanations

    decay degradation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ත්ත
    0.62
    boden
    0.61
     modalités
    0.61
    Concurrency
    0.55
     keselamatan
    0.55
     कक्क
    0.55
    rilor
    0.55
     ओवरटाइम
    0.54
     retorn
    0.54
    地铁
    0.54
    POSITIVE LOGITS
    衰
    0.74
     decays
    0.71
    decay
    0.63
     decaying
    0.63
     decay
    0.60
    يش
    0.59
     Decay
    0.59
    Lat
    0.55
    宛
    0.54
     फ्यू
    0.54
    Act Density 0.000%

    No Known Activations