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

    Neuronpedia

    INDEX
    Explanations

    elliptic curve cryptography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ravés
    0.41
     autorización
    0.41
    存档备份
    0.40
    echolog
    0.40
    贰百
    0.40
    镤
    0.39
    صیٰ
    0.39
    othérapie
    0.38
    क्लेव
    0.38
    CompliancePolicy
    0.38
    POSITIVE LOGITS
    0.63
    ↵↵
    0.58
     (
    0.55
     G
    0.53
    ↵
    0.51
     D
    0.51
    ↵↵↵
    0.48
     \
    0.48
     B
    0.47
      
    0.47
    Act Density 0.001%

    No Known Activations