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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Kb
    -0.07
     suit
    -0.06
    作用
    -0.06
    自负
    -0.06
    愆
    -0.06
     Libertarian
    -0.06
    ircles
    -0.06
    有着
    -0.06
     لكم
    -0.06
    ክ
    -0.06
    POSITIVE LOGITS
    IMATION
    0.07
     jav
    0.07
    _chat
    0.07
     Chrome
    0.06
     trainable
    0.06
    中美
    0.06
     Shanghai
    0.06
     rem
    0.06
    yar
    0.06
    .gca
    0.06
    Act Density 0.021%

    No Known Activations