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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    彻底
    0.81
    absolutely
    0.76
    込め
    0.73
    Fle
    0.72
     особое
    0.72
    contained
    0.71
    Almost
    0.71
     absolutely
    0.71
     anew
    0.70
    Potential
    0.69
    POSITIVE LOGITS
     occurrence
    1.23
    occurrence
    0.97
    ولی
    0.95
     бывает
    0.93
     trait
    0.93
     অমন
    0.91
    occurring
    0.90
     concern
    0.89
    ตรฐาน
    0.87
    情况下
    0.86
    Act Density 2.175%

    No Known Activations