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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    /fire
    -0.08
     çocukların
    -0.07
     closer
    -0.07
    ancybox
    -0.07
    ("----------------
    -0.07
     Constructor
    -0.07
     donation
    -0.06
    Closed
    -0.06
     rekl
    -0.06
    借此
    -0.06
    POSITIVE LOGITS
    ＠
    0.07
    華
    0.07
    係
    0.07
    装甲
    0.07
    縮
    0.07
    战场
    0.07
     narratives
    0.07
    航
    0.06
    Ｅ
    0.06
    �
    0.06
    Act Density 0.011%

    No Known Activations