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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Problems
    0.88
     Probleme
    0.84
     Coordination
    0.80
    訌
    0.77
     Relaxation
    0.77
     ইউনিয়ন
    0.76
     Racism
    0.75
     Reality
    0.75
     Horizon
    0.74
     Gene
    0.73
    POSITIVE LOGITS
    k
    0.83
    ر
    0.77
     defaultdict
    0.77
     avoid
    0.75
     avoiding
    0.75
    цата
    0.74
    ጥር
    0.74
    p
    0.73
    м
    0.73
    ور
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.