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

    Neuronpedia

    INDEX
    Explanations

    Lagrange multipliers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ColumnKind
    0.43
     दस्तक
    0.42
     cốc
    0.42
     linear
    0.42
    stethoscope
    0.41
     tinnitus
    0.41
     lung
    0.41
    鎬
    0.41
     stump
    0.40
     मधुमेह
    0.40
    POSITIVE LOGITS
     Lagrangian
    1.61
     Lagrange
    1.58
    Lag
    1.41
     Lag
    1.19
    Hamilton
    1.18
     Hamilton
    1.16
    Euler
    1.12
     Hamiltonian
    1.09
     Euler
    1.08
     lag
    1.05
    Act Density 0.012%

    No Known Activations