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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    n
    1.09
    u
    0.94
     túi
    0.90
     muon
    0.88
    -
    0.86
    ↵
    0.85
    ía
    0.85
     Upan
    0.84
    quiera
    0.83
    ized
    0.82
    POSITIVE LOGITS
    𝐁
    1.02
    sensor
    0.97
     வகையில்
    0.93
    CTURE
    0.90
    িমূলক
    0.90
    ح
    0.90
    capabilities
    0.89
    ה
    0.88
    lig
    0.88
    ABLE
    0.87
    Act Density 0.227%

    No Known Activations