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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     behaviors
    -0.07
    unas
    -0.07
     vigor
    -0.07
    jal
    -0.07
     âĸ³
    -0.07
     rumor
    -0.07
     catalogs
    -0.06
     favorable
    -0.06
    ialized
    -0.06
    zh
    -0.06
    POSITIVE LOGITS
     lekker
    0.10
    Apart
    0.08
    inspace
    0.07
     suo
    0.07
    rega
    0.07
    expiry
    0.06
     beneficiation
    0.06
     Rica
    0.06
     Apart
    0.06
    roupon
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.