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

    Neuronpedia

    INDEX
    Explanations

    autonomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Profiles
    -0.08
     Gaia
    -0.08
     Concord
    -0.08
     Chine
    -0.08
     Convention
    -0.07
     conventions
    -0.07
    _profiles
    -0.07
    CCIÓN
    -0.07
     convention
    -0.07
    imentation
    -0.07
    POSITIVE LOGITS
     autonomy
    0.10
     empowering
    0.10
     empowerment
    0.09
     Empower
    0.09
     redesigned
    0.09
    leading
    0.09
    Expose
    0.08
     reduzieren
    0.08
     맡
    0.08
    Leading
    0.08
    Act Density 0.010%

    No Known Activations