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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sectors
    -0.07
    NR
    -0.07
    controlled
    -0.07
    ยอม
    -0.07
     Nelson
    -0.07
    任何一个
    -0.07
     GPU
    -0.07
    造福
    -0.07
     Somerset
    -0.07
    .Panel
    -0.07
    POSITIVE LOGITS
    elcome
    0.08
    Italic
    0.07
    最喜欢的
    0.07
    fter
    0.07
    饷
    0.07
    珰
    0.07
    イ
    0.07
    UI
    0.07
     Installer
    0.06
     antique
    0.06
    Act Density 0.088%

    No Known Activations