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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ipedia
    -0.79
     Lash
    -0.78
     Tanz
    -0.69
     Regiment
    -0.69
     Lonely
    -0.67
    ova
    -0.67
     Row
    -0.66
    lund
    -0.66
     Myst
    -0.66
    Gil
    -0.64
    POSITIVE LOGITS
     Principle
    0.68
     aperture
    0.68
     Watts
    0.67
    verages
    0.66
     regress
    0.64
     permit
    0.63
    ãĥ¼ãĤ¯
    0.62
     tariffs
    0.62
     calibr
    0.61
     emissions
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.