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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .—
    -0.09
    bagai
    -0.08
     esteemed
    -0.08
    ược
    -0.08
     Easily
    -0.07
    ,—
    -0.07
    乐队
    -0.07
    Saudi
    -0.07
     pourquoi
    -0.07
    olesterol
    -0.07
    POSITIVE LOGITS
    Li
    0.07
    澄
    0.07
     RH
    0.07
     Jacqu
    0.07
    散布
    0.07
     У
    0.07
     holding
    0.07
     Stream
    0.07
     LIB
    0.06
    进程
    0.06
    Act Density 0.060%

    No Known Activations