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

    Neuronpedia

    INDEX
    Explanations

    intelligence and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intruder
    0.47
    anyi
    0.41
    ेद
    0.41
     روسیه
    0.39
    bedo
    0.38
     انجام
    0.37
    ผ่าน
    0.37
     intruders
    0.37
     예술
    0.37
    וני
    0.37
    POSITIVE LOGITS
    ندن
    0.46
     definición
    0.46
     símbolo
    0.46
    рії
    0.45
     şeklinde
    0.45
     çarp
    0.45
     দক্ষিণে
    0.45
     CharPtr
    0.45
    ícias
    0.44
     médioc
    0.44
    Act Density 0.005%

    No Known Activations