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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ixels
    -0.66
     Tests
    -0.66
     Turtles
    -0.65
     Marketable
    -0.63
     Plain
    -0.63
     Charges
    -0.63
    eele
    -0.61
     Builder
    -0.60
    airo
    -0.59
     Kits
    -0.59
    POSITIVE LOGITS
    ILY
    0.85
    ridor
    0.81
    76561
    0.74
    pole
    0.68
    pend
    0.65
    regon
    0.64
    MpServer
    0.64
    APS
    0.64
    exit
    0.63
    gnu
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.