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

    Neuronpedia

    INDEX
    Explanations

    arranging or ordering items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    1.49
    1
    1.40
     a
    1.09
     at
    1.07
     is
    1.01
     so
    0.97
     to
    0.96
     in
    0.95
    3
    0.94
    '
    0.83
    POSITIVE LOGITS
     Arrangement
    1.02
    િ
    0.97
    is
    0.96
     فونی
    0.96
    ور
    0.96
     Arrang
    0.96
    us
    0.95
    اب
    0.91
     Feuilles
    0.90
    アレンジ
    0.89
    Act Density 0.004%

    No Known Activations