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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .classList
    -0.07
     Rex
    -0.07
    _collection
    -0.07
     level
    -0.07
    特殊情况
    -0.07
     Saras
    -0.07
     clearance
    -0.07
     coefficient
    -0.07
     Swal
    -0.07
    坐
    -0.06
    POSITIVE LOGITS
    难以
    0.08
     Memories
    0.07
    _deriv
    0.07
    fu
    0.07
    切断
    0.06
    🤖
    0.06
    Modified
    0.06
    🔎
    0.06
    _new
    0.06
     другими
    0.06
    Act Density 0.003%

    No Known Activations