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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Colo
    -0.07
     Bộ
    -0.07
    nob
    -0.07
    Shock
    -0.07
     Filipino
    -0.07
    صح
    -0.07
    性能
    -0.06
     warranted
    -0.06
    nb
    -0.06
    Saudi
    -0.06
    POSITIVE LOGITS
    订单
    0.08
    _likes
    0.07
    _posts
    0.07
     diffs
    0.07
    火花
    0.07
    weets
    0.07
    .Flags
    0.07
     birds
    0.07
    .rect
    0.07
     had
    0.07
    Act Density 0.061%

    No Known Activations