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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fore
    -0.07
    _MET
    -0.07
    .).
    -0.07
     Sno
    -0.06
    Derived
    -0.06
    CONT
    -0.06
    掂
    -0.06
    GMT
    -0.06
    Ḟ
    -0.06
    .Second
    -0.06
    POSITIVE LOGITS
     newPath
    0.08
    境外
    0.07
    位置
    0.07
     recursion
    0.07
    🅱
    0.07
    (Op
    0.07
    uples
    0.07
    部位
    0.07
    membership
    0.07
    닛
    0.07
    Act Density 0.026%

    No Known Activations