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

    Neuronpedia

    INDEX
    Explanations

    encryption and keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Woman
    -0.09
     raggi
    -0.09
     Woman
    -0.09
     cheddar
    -0.09
     Fiverr
    -0.08
     arred
    -0.08
     tobacco
    -0.08
     Lemon
    -0.08
     женщины
    -0.08
    ček
    -0.08
    POSITIVE LOGITS
     secrets
    0.09
     securely
    0.09
     गो
    0.09
    _SECRET
    0.09
    钥
    0.08
    (secret
    0.08
     distributed
    0.08
    密
    0.08
     वित
    0.08
    秘密
    0.08
    Act Density 0.009%

    No Known Activations