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

    Neuronpedia

    INDEX
    Explanations

    location, proximity, possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cons
    0.43
    Согласно
    0.41
     ज़
    0.37
    Lo
    0.36
    ்ப
    0.36
     Cl
    0.35
    ăm
    0.35
     Согласно
    0.34
     根据
    0.34
    évén
    0.34
    POSITIVE LOGITS
     عند
    0.61
     la
    0.53
     upon
    0.51
     lângă
    0.51
     عنده
    0.47
     عندك
    0.46
     عندها
    0.46
     behind
    0.45
     عندي
    0.45
    عند
    0.44
    Act Density 0.000%

    No Known Activations