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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Belg
    -0.71
    ãĥĨ
    -0.68
     Erd
    -0.66
    ãĤ±
    -0.66
    Ax
    -0.65
     opposite
    -0.64
     intellig
    -0.64
     abdom
    -0.64
    ãĤ¶
    -0.62
    1950
    -0.61
    POSITIVE LOGITS
    VERTISEMENT
    0.88
    PLA
    0.75
    enegger
    0.74
     ILCS
    0.74
    ICLE
    0.72
    swer
    0.72
    erness
    0.71
    TION
    0.70
     Loans
    0.70
    INESS
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.