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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens related to password fields or credentials (e.g. “password,” “senha”), i.e. it detects password‐type entries in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     viewBox
    -0.07
     IDX
    -0.07
    Fs
    -0.06
     Elliot
    -0.06
     IMS
    -0.06
    _RAW
    -0.06
    .feature
    -0.06
     лет
    -0.06
     vốn
    -0.06
    енні
    -0.06
    POSITIVE LOGITS
    _cfg
    0.07
     Personen
    0.06
    othy
    0.06
    _PASSWORD
    0.06
    online
    0.06
     대통령
    0.06
     '');↵
    0.06
     Capt
    0.06
    kanı
    0.06
    )\
    0.06
    Act Density 0.006%

    No Known Activations