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

    Neuronpedia

    INDEX
    Explanations

    current index or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    税务
    0.47
    隗
    0.45
    واری
    0.45
     پرست
    0.43
    伟
    0.42
    ธรรม
    0.41
    Loksatta
    0.41
     साम्राज्य
    0.41
     голу
    0.41
    传奇
    0.41
    POSITIVE LOGITS
    当前
    0.52
    index
    0.51
     selected
    0.51
     当前
    0.47
    id
    0.46
     current
    0.46
    idx
    0.46
    selected
    0.46
    int
    0.45
     neighboring
    0.45
    Act Density 0.294%

    No Known Activations