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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     преду
    0.43
     fanfare
    0.41
    эро
    0.41
    χαν
    0.39
     دهید
    0.38
    先行
    0.37
     ет
    0.37
    ِد
    0.37
    ────────
    0.37
     තා
    0.36
    POSITIVE LOGITS
     ionization
    0.42
     لقي
    0.42
     scale
    0.40
    consistency
    0.39
     just
    0.39
    localized
    0.38
     수도
    0.38
     renormalization
    0.37
     conjugacy
    0.37
     Just
    0.37
    Act Density 0.010%

    No Known Activations