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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    é¾
    -1.09
    Maps
    -0.74
    ictionary
    -0.72
    CHO
    -0.72
    ãĥ¼ãĥ
    -0.69
     Anarchy
    -0.69
    ndum
    -0.67
    tick
    -0.66
    ebted
    -0.66
    agonists
    -0.65
    POSITIVE LOGITS
     pav
    0.69
     tranquil
    0.68
     chairs
    0.67
     seniors
    0.64
     rodent
    0.64
     retirees
    0.64
    reens
    0.62
     POS
    0.61
     chair
    0.61
     poised
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.