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

    Neuronpedia

    INDEX
    Explanations

    recent years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yapılacak
    0.50
     tomorrow
    0.49
     something
    0.48
     Old
    0.44
     expected
    0.43
     will
    0.42
     soda
    0.42
    ף
    0.42
    S
    0.41
    r
    0.41
    POSITIVE LOGITS
     منذ
    1.48
    近年
    1.38
    近年来
    1.38
     최근
    1.36
     पिछले
    1.31
     lately
    1.30
     since
    1.30
     depuis
    1.27
     sejak
    1.26
    最近
    1.23
    Act Density 0.072%

    No Known Activations