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

    Neuronpedia

    INDEX
    Explanations

    valve control and response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ката
    0.52
    ة
    0.47
    ricanes
    0.46
    inea
    0.45
    לה
    0.45
     বৃত্তান্ত
    0.45
     velocidade
    0.45
     multipart
    0.45
    امي
    0.44
     altitudes
    0.43
    POSITIVE LOGITS
     सेक्शन
    0.45
     Section
    0.43
     Bew
    0.41
    பிள்
    0.40
    왑
    0.40
    yin
    0.39
     Sank
    0.39
    Posting
    0.38
    ulating
    0.38
    ย
    0.38
    Act Density 0.004%

    No Known Activations