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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fear
    -0.07
     briefly
    -0.07
     Laboratories
    -0.07
     forecasting
    -0.07
    osl
    -0.06
    )did
    -0.06
     myfile
    -0.06
     stupid
    -0.06
    Installer
    -0.06
     PriorityQueue
    -0.06
    POSITIVE LOGITS
    rve
    0.07
     움직
    0.07
    elter
    0.06
     vbCrLf
    0.06
     (_.
    0.06
    .cent
    0.06
    profession
    0.06
    ysical
    0.06
     꼭
    0.06
    QA
    0.06
    Act Density 0.042%

    No Known Activations