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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     возраст
    -0.08
    .IsNullOr
    -0.07
     estará
    -0.07
     이번
    -0.07
     vmin
    -0.07
    户籍
    -0.07
     czę
    -0.06
     vere
    -0.06
    �
    -0.06
     רשאי
    -0.06
    POSITIVE LOGITS
    -master
    0.08
    icked
    0.07
     stove
    0.07
    -short
    0.07
     magnet
    0.07
     dynasty
    0.07
    重重
    0.07
     READ
    0.07
     Prophet
    0.06
    -low
    0.06
    Act Density 0.003%

    No Known Activations