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

    Neuronpedia

    INDEX
    Explanations

    locations and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உடலில்
    0.46
     onsite
    0.45
    身上的
    0.45
     worldwide
    0.44
    放在
    0.44
     নিজেই
    0.43
     throughout
    0.43
    事前に
    0.43
     upfront
    0.43
     შემდეგ
    0.42
    POSITIVE LOGITS
    にある
    0.46
     ድረስ
    0.45
     есть
    0.44
    才是
    0.43
    では
    0.43
     هست
    0.42
     όπου
    0.42
    设有
    0.41
    有個
    0.40
    景象
    0.40
    Act Density 0.055%

    No Known Activations