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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vl
    -0.85
    ufact
    -0.83
     shenan
    -0.80
    eson
    -0.75
     destro
    -0.74
    olini
    -0.72
     Dro
    -0.72
    erker
    -0.71
     Korra
    -0.70
     stack
    -0.70
    POSITIVE LOGITS
    âĵĺ
    0.81
    true
    0.76
    heit
    0.71
    omal
    0.68
    Correct
    0.66
    2010
    0.66
    ãĤ¼ãĤ¦ãĤ¹
    0.66
    ãĥ´ãĤ¡
    0.66
    arest
    0.64
    Meg
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.