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

    Neuronpedia

    INDEX
    Explanations

    encryption and decryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qualific
    0.59
     중심
    0.46
     квали
    0.44
    qualification
    0.43
    改善
    0.43
    蟑
    0.42
    趵
    0.42
    GetComponents
    0.42
     Qualification
    0.41
     дости
    0.41
    POSITIVE LOGITS
     encryption
    2.05
     encrypt
    2.03
     encrypted
    2.02
     Encryption
    1.90
     decrypt
    1.89
     decryption
    1.84
    encrypt
    1.73
    encrypted
    1.71
    Encryption
    1.71
    encryption
    1.68
    Act Density 0.076%

    No Known Activations