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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    高中
    -0.08
    ulent
    -0.08
    洋葱
    -0.07
    📢
    -0.07
    =(
    -0.07
    哚
    -0.07
     niño
    -0.07
    跺
    -0.07
     polymer
    -0.07
    arez
    -0.06
    POSITIVE LOGITS
     integrity
    0.07
    _hal
    0.07
    𝐊
    0.06
    乾隆
    0.06
    }`);↵
    0.06
    \Factory
    0.06
    诸侯
    0.06
     كب
    0.06
    Ц
    0.06
    łem
    0.06
    Act Density 0.000%

    No Known Activations