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

    Neuronpedia

    INDEX
    Explanations

    sum and pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     networking
    0.50
     Regression
    0.43
     regression
    0.43
    ysł
    0.42
     iremos
    0.42
     outperforms
    0.41
     Hemen
    0.40
     Networking
    0.39
     framework
    0.39
     CPE
    0.39
    POSITIVE LOGITS
     мер
    0.44
     நாள்
    0.41
    ज्ञा
    0.39
    доз
    0.39
    ⺀
    0.39
    ложить
    0.38
     اوقات
    0.38
    љ
    0.38
    חו
    0.38
    违
    0.37
    Act Density 0.000%

    No Known Activations