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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     soma
    -0.07
     biomass
    -0.07
    讨论
    -0.07
    )$
    -0.07
     issue
    -0.07
    ока
    -0.07
    OST
    -0.06
     extracting
    -0.06
     embargo
    -0.06
    হ
    -0.06
    POSITIVE LOGITS
     תמיד
    0.08
    为抓
    0.07
    Verbose
    0.07
    priority
    0.07
    <Vec
    0.07
     السورية
    0.07
    PushButton
    0.07
    Лени
    0.07
    -shaped
    0.07
     Jacqu
    0.07
    Act Density 0.116%

    No Known Activations