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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    雍
    -0.07
    א
    -0.07
     powerless
    -0.07
    bye
    -0.07
     dereg
    -0.07
     ano
    -0.06
    _inp
    -0.06
    outing
    -0.06
     DIR
    -0.06
     Во
    -0.06
    POSITIVE LOGITS
    还是
    0.07
    .Session
    0.07
    することが
    0.07
    _weather
    0.06
    .Guna
    0.06
     cambios
    0.06
    .tableView
    0.06
    .websocket
    0.06
    Tower
    0.06
    政府部门
    0.06
    Act Density 0.155%

    No Known Activations