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

    Neuronpedia

    INDEX
    Explanations

    names of people and companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이
    0.88
     Instagram
    0.86
     Airbnb
    0.84
     instagram
    0.83
     girlfriend
    0.83
     ✅
    0.83
    வலி
    0.82
     CSS
    0.80
     로
    0.79
     문의
    0.79
    POSITIVE LOGITS
    i
    0.82
     وتع
    0.78
    dav
    0.74
    ივ
    0.71
    י
    0.70
    lighting
    0.70
    ي
    0.70
    tedir
    0.69
    teach
    0.69
     pemberian
    0.69
    Act Density 0.309%

    No Known Activations