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

    Neuronpedia

    INDEX
    Explanations

    dx, dt in calculus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ципа
    0.50
     القيمه
    0.42
     گزینه
    0.41
    Penumpang
    0.41
    窍
    0.40
    셔서
    0.40
    ூழ
    0.39
     პროგრამ
    0.39
    例外
    0.39
    ꉂ
    0.39
    POSITIVE LOGITS
     dx
    1.43
     dt
    1.24
    dx
    1.21
    dt
    1.00
     dy
    1.00
     DX
    0.94
     differential
    0.91
     dz
    0.89
     dq
    0.88
     dT
    0.86
    Act Density 0.011%

    No Known Activations