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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     carbs
    -0.07
    _collection
    -0.07
     Successful
    -0.07
    ':['
    -0.06
    (Context
    -0.06
     Illum
    -0.06
    对未来
    -0.06
     Vul
    -0.06
    生素
    -0.06
    .Views
    -0.06
    POSITIVE LOGITS
    变化
    0.07
    迁
    0.07
    bond
    0.07
    塝
    0.07
    每年
    0.07
    _PHASE
    0.07
     hoje
    0.07
    ocusing
    0.07
    modes
    0.07
    quota
    0.06
    Act Density 0.012%

    No Known Activations