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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    FER
    -0.07
     stunned
    -0.07
    二手
    -0.07
     strand
    -0.07
     форму
    -0.07
    弓
    -0.07
    珝
    -0.07
     stuffing
    -0.06
    .accuracy
    -0.06
     courtesy
    -0.06
    POSITIVE LOGITS
    Bean
    0.06
    僔
    0.06
     Observer
    0.06
     Petsc
    0.06
    בת
    0.06
    母亲
    0.06
    uje
    0.06
    яз
    0.06
     dest
    0.06
    arsing
    0.06
    Act Density 0.001%

    No Known Activations