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

    Neuronpedia

    INDEX
    Explanations

    high degree or level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     వలన
    0.77
    眄
    0.70
     basis
    0.70
    㘟
    0.68
    身上的
    0.66
     製造
    0.66
     facets
    0.66
     중심
    0.66
     ആശ
    0.65
     Val
    0.65
    POSITIVE LOGITS
    very
    1.31
    quite
    1.30
     very
    1.23
     quite
    1.21
     весьма
    1.17
     очень
    1.15
    slightly
    1.14
    extremely
    1.13
     oldukça
    1.11
     rất
    1.10
    Act Density 0.001%

    No Known Activations