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

    Neuronpedia

    INDEX
    Explanations

    references to passwords and password-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    password

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.77
    <unused41>
    -0.65
    <unused28>
    -0.65
    <unused16>
    -0.64
    <unused8>
    -0.64
    [@BOS@]
    -0.64
    <unused23>
    -0.64
    <unused43>
    -0.64
    <unused17>
    -0.64
    <unused14>
    -0.64
    POSITIVE LOGITS
    Password
    0.65
     password
    0.64
    PasswordEncoder
    0.59
    PasswordField
    0.56
     Password
    0.55
     passwords
    0.52
     setPassword
    0.50
     PASSWORD
    0.48
    password
    0.47
    PASSWORD
    0.45
    Act Density 0.009%

    No Known Activations