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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tornando
    1.59
     vivido
    1.53
    ak
    1.47
    ве
    1.44
    पृ
    1.44
     respectivas
    1.37
     determinadas
    1.36
     Sekarang
    1.36
     nerve
    1.35
    ו
    1.35
    POSITIVE LOGITS
     curb
    1.62
    tive
    1.59
    soph
    1.56
    ✓
    1.53
    єї
    1.50
     तोड़
    1.48
    ꯣ
    1.46
    fight
    1.45
    ḫ
    1.44
     _,
    1.42
    Act Density 0.000%

    No Known Activations