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

    Neuronpedia

    INDEX
    Explanations

    overlaps and intersections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☜
    0.47
     установлен
    0.41
     శా
    0.40
    Estab
    0.40
     meth
    0.39
     localizado
    0.38
    柛
    0.38
    嗓
    0.38
     reserving
    0.38
     aaa
    0.38
    POSITIVE LOGITS
    overlaps
    0.47
     overlaps
    0.43
     overlap
    0.43
     overlapped
    0.42
    overlap
    0.39
    还
    0.39
    intersection
    0.39
    敬
    0.38
     overlapping
    0.38
    发起
    0.38
    Act Density 0.001%

    No Known Activations