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

    Neuronpedia

    INDEX
    Explanations

    spin, energy, state, electrons, eigenvalue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nepali
    0.86
     caches
    0.76
     batch
    0.74
     flakes
    0.72
     feedbacks
    0.70
     logged
    0.70
     webhook
    0.70
     tourism
    0.69
     batches
    0.69
     feedback
    0.69
    POSITIVE LOGITS
     energies
    1.30
     orbitals
    1.25
     energy
    1.25
     energías
    1.21
     vibrational
    1.19
     electronic
    1.17
     Energies
    1.17
     eigenvalues
    1.17
     Energy
    1.16
    energy
    1.16
    Act Density 0.125%

    No Known Activations