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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    鲥
    -0.07
    _prime
    -0.07
     الصحة
    -0.06
    文旅
    -0.06
    娘娘
    -0.06
    .attrib
    -0.06
    法律顾问
    -0.06
    izards
    -0.06
     whore
    -0.06
    ॰
    -0.06
    POSITIVE LOGITS
    preh
    0.07
    ㄱ
    0.07
    _VECTOR
    0.07
    (fe
    0.07
    郑重
    0.06
     Schedule
    0.06
    য
    0.06
     interested
    0.06
    হ
    0.06
     stacks
    0.06
    Act Density 0.004%

    No Known Activations