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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    fung
    -0.07
     grasp
    -0.07
    ₓ
    -0.07
    设计器
    -0.07
    院副院长
    -0.06
    Sex
    -0.06
    מעצב
    -0.06
    >>()
    -0.06
     Alignment
    -0.06
    stashop
    -0.06
    POSITIVE LOGITS
     chocolates
    0.07
    udence
    0.07
    _documents
    0.07
    _ram
    0.07
    俄
    0.06
    润滑油
    0.06
    硼
    0.06
    Flying
    0.06
    عم
    0.06
    后勤
    0.06
    Act Density 0.001%

    No Known Activations