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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    通販
    0.68
    opherol
    0.66
     வேறு
    0.62
    ̡
    0.61
    ResponseBody
    0.60
    ̩
    0.59
     иной
    0.58
    colorbar
    0.58
     الأخرى
    0.57
    ᆭ
    0.57
    POSITIVE LOGITS
     initial
    4.50
    Initial
    4.06
     first
    4.04
     initially
    4.01
     Initial
    3.98
    initial
    3.94
     inital
    3.90
     initiale
    3.78
     inicial
    3.71
    first
    3.66
    Act Density 6.394%

    No Known Activations