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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aronder
    -0.37
    occuper
    -0.32
     Con
    -0.32
     
    -0.31
     World
    -0.31
    ↵
    -0.30
     đồ
    -0.29
     called
    -0.29
     settled
    -0.29
     [
    -0.28
    POSITIVE LOGITS
     informée
    1.16
    parsedMessage
    1.13
    misa
    1.13
    хьтан
    0.91
    تقاوى
    0.88
    Tikang
    0.88
     Numerade
    0.87
     kasarigan
    0.87
    0.86
     nahilalakip
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.