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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    涂抹
    -0.07
    تط
    -0.07
     Retro
    -0.07
    ˗
    -0.07
    lust
    -0.07
    overnment
    -0.07
    تكن
    -0.07
     clandest
    -0.06
     właśnie
    -0.06
    背叛
    -0.06
    POSITIVE LOGITS
    BLEM
    0.07
    _feat
    0.07
    我说
    0.07
     zeroes
    0.07
    万亿元
    0.07
    urgy
    0.07
     ==============================================================
    0.07
    ,img
    0.06
    .TestTools
    0.06
     illustrates
    0.06
    Act Density 0.006%

    No Known Activations