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

    Neuronpedia

    INDEX
    Explanations

    mismatched expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    حمد
    0.49
    廝
    0.48
     quell
    0.47
     والدین
    0.47
    ﻴ
    0.46
    Parents
    0.46
    وي
    0.46
     перший
    0.46
    Hamburg
    0.46
    Pago
    0.45
    POSITIVE LOGITS
     discrete
    0.47
     surprises
    0.43
     chops
    0.42
    ase
    0.42
     tricks
    0.41
     digestive
    0.41
    inat
    0.41
     divided
    0.39
    astar
    0.39
     CharPtr
    0.38
    Act Density 0.013%

    No Known Activations