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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Sidebar
    -0.07
     bú
    -0.07
     Pickup
    -0.07
    合规
    -0.07
    屏
    -0.06
    ku
    -0.06
    底线
    -0.06
    io
    -0.06
    _decrypt
    -0.06
    compact
    -0.06
    POSITIVE LOGITS
    ?,?,
    0.08
    てしま
    0.08
    翱
    0.07
    .Buttons
    0.07
    Maria
    0.07
    嵊
    0.07
    .reward
    0.07
     Natal
    0.07
     miejs
    0.07
    .createQuery
    0.07
    Act Density 0.002%

    No Known Activations