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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Level
    0.74
    â
    0.73
    Levels
    0.73
    ier
    0.72
    Workspace
    0.71
    aña
    0.71
    are
    0.70
     organizacional
    0.70
    态
    0.70
    level
    0.69
    POSITIVE LOGITS
     база
    0.82
     prisão
    0.80
     ব্রহ্ম
    0.76
     chopsticks
    0.76
     이건
    0.75
     medis
    0.74
    риб
    0.74
    手術
    0.74
    లుగా
    0.73
     meditation
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.