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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    psons
    -0.94
    flix
    -0.91
    gallery
    -0.84
    gru
    -0.81
     Minotaur
    -0.77
    reprene
    -0.74
    chard
    -0.74
     Zup
    -0.72
    tenance
    -0.72
    lov
    -0.71
    POSITIVE LOGITS
     own
    0.90
     opponent
    0.87
    ¥ŀ
    0.83
     homeland
    0.82
     inclination
    0.82
     temperament
    0.82
     earthly
    0.80
     theological
    0.80
     schooling
    0.79
     favoured
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.