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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Libre
    -0.83
     Mex
    -0.77
     Enrique
    -0.74
    net
    -0.72
     Net
    -0.67
     firewall
    -0.66
     Moreno
    -0.66
    obal
    -0.66
     Nou
    -0.66
    wan
    -0.64
    POSITIVE LOGITS
    Accessory
    0.76
    ilitarian
    0.69
    ŃĶ
    0.69
    SHARE
    0.67
    ikh
    0.67
    Personal
    0.66
    amount
    0.65
    benefit
    0.64
    isable
    0.64
    Times
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.