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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     restorations
    0.87
     Fakat
    0.80
     forests
    0.77
     dislocations
    0.77
     traverses
    0.77
     warns
    0.76
     restores
    0.76
     протяжении
    0.75
     prothorax
    0.75
     природе
    0.74
    POSITIVE LOGITS
    ا
    0.83
    𝙚
    0.83
    𝙤
    0.82
    い
    0.81
    𝙀
    0.79
    𝑦
    0.78
    این
    0.77
    Altitude
    0.77
     Monument
    0.76
    ut
    0.75
    Act Density 0.000%

    No Known Activations