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

    Neuronpedia

    INDEX
    Explanations

    days and dates, weather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻹ
    0.45
     היו
    0.41
    Cleveland
    0.40
    镛
    0.40
    绩
    0.39
     রহিয়াছে
    0.39
    䍘
    0.38
     Gabri
    0.38
     expresó
    0.38
    अपना
    0.38
    POSITIVE LOGITS
     nad
    0.39
    <span>
    0.37
     r
    0.35
     redshift
    0.34
    yyyyyyyy
    0.34
    eeee
    0.34
     ]
    0.33
     နောက်
    0.33
    aso
    0.33
    ovel
    0.33
    Act Density 0.001%

    No Known Activations