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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     læ
    -0.08
     undercut
    -0.07
    .backend
    -0.07
     コ
    -0.07
    .friend
    -0.07
    /rand
    -0.07
    /q
    -0.07
    ClearColor
    -0.07
     sequel
    -0.07
    summary
    -0.06
    POSITIVE LOGITS
    身边
    0.07
     жиз
    0.07
    nych
    0.07
    逾期
    0.07
     çalışmalar
    0.07
    交通
    0.07
    Disk
    0.07
     đỉnh
    0.06
    中枢
    0.06
    _TOKEN
    0.06
    Act Density 0.002%

    No Known Activations