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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    prom
    0.39
    ki
    0.36
    ly
    0.36
    ता
    0.36
     الجيش
    0.34
    annya
    0.33
    kehr
    0.33
     Como
    0.33
    iding
    0.33
    так
    0.33
    POSITIVE LOGITS
    ಬ್ಬಳ್ಳಿ
    0.41
     화
    0.41
    %;
    0.40
    અ
    0.40
    yoruz
    0.40
     osh
    0.40
     Nếu
    0.39
    យើង
    0.39
    <unused2046>
    0.38
    0.38
    Act Density 0.500%

    No Known Activations