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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .zz
    -0.07
     gravid
    -0.07
    .yellow
    -0.07
    ᶏ
    -0.07
    >.
    -0.07
    胫
    -0.07
    kov
    -0.07
    Ill
    -0.07
    ﯽ
    -0.06
    rawer
    -0.06
    POSITIVE LOGITS
    냈
    0.07
    verified
    0.07
     cargo
    0.07
     Depot
    0.07
     moderation
    0.07
    섰
    0.07
    长沙市
    0.07
     Boost
    0.06
    [label
    0.06
    עלות
    0.06
    Act Density 0.005%

    No Known Activations