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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ামি
    0.48
     funcionar
    0.47
     exchanger
    0.44
     magnis
    0.44
    ენა
    0.44
     relinqu
    0.43
    eneva
    0.42
    追
    0.42
    exam
    0.42
     abandonar
    0.42
    POSITIVE LOGITS
    и
    0.52
    ா
    0.46
    да
    0.45
     Ло
    0.45
    зі
    0.44
    gladbach
    0.44
     فوجی
    0.44
    ğunu
    0.44
     레이
    0.44
    桻
    0.43
    Act Density 0.000%

    No Known Activations