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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🍊
    -0.08
    _props
    -0.07
     own
    -0.07
     boon
    -0.07
    올
    -0.06
    "}}
    -0.06
    .Try
    -0.06
     Gilles
    -0.06
    ↺
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
     the
    0.08
     password
    0.08
     punishable
    0.07
     chocolate
    0.07
    Serializer
    0.07
     and
    0.07
    _password
    0.07
    Percentage
    0.07
    Password
    0.07
    Published
    0.07
    Act Density 0.017%

    No Known Activations