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

    Neuronpedia

    INDEX
    Explanations

    password complexity and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decrypted
    0.50
     login
    0.49
     credentials
    0.47
     passwords
    0.46
     паро
    0.42
    Credentials
    0.42
     decryption
    0.41
    用户名
    0.41
     password
    0.40
     비밀
    0.40
    POSITIVE LOGITS
     Strength
    0.82
    strength
    0.80
     strength
    0.78
    Strength
    0.75
    強度
    0.71
    強
    0.71
     enforce
    0.68
    strong
    0.64
     strong
    0.64
    强
    0.64
    Act Density 0.005%

    No Known Activations