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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     enduro
    1.02
     decarbon
    1.00
     mediocr
    0.93
     Fedora
    0.91
     foothold
    0.90
     merino
    0.89
     martingale
    0.88
     germanium
    0.88
     mediocre
    0.88
     DeFi
    0.88
    POSITIVE LOGITS
    نق
    0.73
     Misalnya
    0.72
    ن
    0.70
     properties
    0.69
     PROPERTIES
    0.69
    MAN
    0.68
    子
    0.68
    setLevel
    0.66
    ار
    0.65
    ל
    0.64
    Act Density 0.000%

    No Known Activations