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

    Neuronpedia

    INDEX
    Explanations

    self-awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wc
    -0.06
    _nv
    -0.06
    یت
    -0.06
     sociale
    -0.06
     Gets
    -0.06
    _sensitive
    -0.06
    heets
    -0.06
    qx
    -0.06
    ственных
    -0.06
    _SOL
    -0.06
    POSITIVE LOGITS
     Voy
    0.07
     Bracket
    0.07
    .MouseEventHandler
    0.06
     whistleblower
    0.06
    .ALIGN
    0.06
     Dedicated
    0.06
    .GetResponse
    0.06
     elim
    0.06
     Freak
    0.06
     extension
    0.06
    Act Density 0.053%

    No Known Activations