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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     acknowledging
    -0.07
     suc
    -0.07
     Kb
    -0.06
    _en
    -0.06
    =yes
    -0.06
     radioactive
    -0.06
     exhaustive
    -0.06
     окружа
    -0.06
    uciones
    -0.06
     Tử
    -0.06
    POSITIVE LOGITS
    ifter
    0.07
    止损
    0.07
    🐟
    0.07
    .getElementsByName
    0.07
    delegate
    0.07
    🗽
    0.06
    حظ
    0.06
    阿姨
    0.06
    �
    0.06
    沣
    0.06
    Act Density 0.086%

    No Known Activations