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

    Neuronpedia

    INDEX
    Explanations

    encryption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lou
    -0.07
     Table
    -0.07
    602
    -0.07
     towel
    -0.07
     Submission
    -0.07
     adaptive
    -0.07
    61
    -0.07
    /background
    -0.07
    .AD
    -0.07
    'es
    -0.06
    POSITIVE LOGITS
    crypt
    0.08
    Crypt
    0.08
     encrypt
    0.07
     Encrypt
    0.07
     Crypt
    0.07
    encrypt
    0.07
    .decrypt
    0.07
    暗
    0.07
    riott
    0.06
     encryption
    0.06
    Act Density 0.012%

    No Known Activations