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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Notably
    0.94
    <unused2182>
    0.90
    jadi
    0.88
    rainte
    0.87
     Notably
    0.86
     значит
    0.85
    Neben
    0.85
     itaque
    0.85
    नाडु
    0.83
    ையடுத்து
    0.81
    POSITIVE LOGITS
      
    1.12
     وذلك
    0.86
    、
    0.85
     ஆகியவற்ற
    0.82
    ↵
    0.81
     ஆகியவை
    0.81
    "
    0.78
       
    0.76
    .)
    0.76
     ஆகிய
    0.72
    Act Density 0.553%

    No Known Activations