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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    loomberg
    -0.08
     dù
    -0.07
    询问
    -0.07
    Dire
    -0.07
    髓
    -0.07
    fuse
    -0.07
    ยา
    -0.07
    sock
    -0.07
    不仅要
    -0.07
    鹘
    -0.07
    POSITIVE LOGITS
    activité
    0.08
    .bi
    0.08
    עים
    0.07
     ANC
    0.06
    ⁑
    0.06
     Organizer
    0.06
    äter
    0.06
    rgan
    0.06
    隩
    0.06
    優惠
    0.06
    Act Density 0.001%

    No Known Activations