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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _origin
    -0.09
     hypert
    -0.08
     educ
    -0.07
    治理
    -0.07
    Unlock
    -0.07
    irling
    -0.06
     penetrated
    -0.06
    ידוע
    -0.06
    Blockchain
    -0.06
    🔖
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    signature
    0.07
     awesome
    0.07
    вой
    0.06
     Kris
    0.06
     гер
    0.06
     Gä
    0.06
    .Buffer
    0.06
    .hardware
    0.06
    〼
    0.06
    Act Density 0.040%

    No Known Activations