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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    フラー
    0.49
    侑
    0.45
     alred
    0.44
    ួក
    0.44
     CLIENTI
    0.44
    jami
    0.43
     offences
    0.43
    offline
    0.43
     дохода
    0.43
     delitos
    0.42
    POSITIVE LOGITS
    '
    0.57
    变
    0.57
     Paleo
    0.52
     Politiker
    0.47
    に
    0.47
    宗旨
    0.47
    中
    0.46
    认为
    0.46
    ه
    0.46
    ز
    0.46
    Act Density 0.000%

    No Known Activations