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

    Neuronpedia

    INDEX
    Explanations

    cryptographic primes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skincare
    1.00
     mindfulness
    0.86
     snapshot
    0.86
     Oahu
    0.81
     vaping
    0.80
     sagging
    0.78
     sensory
    0.78
     Sensory
    0.78
     perro
    0.77
     impartiality
    0.76
    POSITIVE LOGITS
     crypt
    1.52
     cryptography
    1.48
     Crypt
    1.47
     cryptographic
    1.45
    Crypt
    1.39
    crypt
    1.38
     क्रिप्ट
    1.35
    Cryptography
    1.32
     prime
    1.24
     primes
    1.24
    Act Density 0.509%

    No Known Activations