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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Jo
    -0.07
    יצ
    -0.07
    ভ
    -0.07
     Mojo
    -0.07
    Dist
    -0.07
    ồn
    -0.07
    _DAYS
    -0.07
    搬
    -0.07
     يست
    -0.07
     Pickup
    -0.06
    POSITIVE LOGITS
     ////
    0.06
     ---------
    0.06
    缩减
    0.06
    нятие
    0.06
    اهل
    0.06
    简化
    0.06
    _Number
    0.06
    什麽
    0.06
    缺席
    0.06
    ropdown
    0.06
    Act Density 0.004%

    No Known Activations