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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ти
    0.95
    О
    0.88
    ק
    0.81
    ко
    0.80
    م
    0.80
    ك
    0.80
    та
    0.79
    א
    0.75
    yloxy
    0.74
     Says
    0.74
    POSITIVE LOGITS
     concerted
    0.95
     purport
    0.93
     cube
    0.93
     detachable
    0.93
     fleet
    0.91
     swarm
    0.90
     meios
    0.89
     knight
    0.88
     hump
    0.87
     foothold
    0.87
    Act Density 0.000%

    No Known Activations