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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     oc
    -0.08
    (Matrix
    -0.07
    🌳
    -0.07
     تو
    -0.07
    تسويق
    -0.07
     rowNum
    -0.07
    거리
    -0.07
     cider
    -0.06
    🌄
    -0.06
     wygląda
    -0.06
    POSITIVE LOGITS
    ተ
    0.07
    敖
    0.07
    Playable
    0.07
    拉动
    0.07
    運動
    0.07
    𝗘
    0.06
    ード
    0.06
    _one
    0.06
    ე
    0.06
    _refs
    0.06
    Act Density 0.003%

    No Known Activations