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

    Neuronpedia

    INDEX
    Explanations

    theoretical physics and cosmology mysteries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    睑
    0.45
     Trainer
    0.42
     factores
    0.39
    🧈
    0.39
     xls
    0.39
     संस्कार
    0.39
    ację
    0.38
     clinically
    0.38
     hygienic
    0.38
     Maked
    0.37
    POSITIVE LOGITS
     physicists
    1.84
     physics
    1.63
     physicist
    1.63
     Physics
    1.61
    Physics
    1.55
    physics
    1.45
     Physic
    1.41
     astrophysics
    1.41
     astrophys
    1.35
     PHYSICS
    1.31
    Act Density 0.028%

    No Known Activations