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

    Neuronpedia

    INDEX
    Explanations

    Emancipation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minimalist
    -0.09
    Standard
    -0.08
    Brain
    -0.08
    PURE
    -0.08
    _SETUP
    -0.08
    _opt
    -0.08
    Setup
    -0.08
    Ampl
    -0.08
    Analog
    -0.08
    _setup
    -0.08
    POSITIVE LOGITS
     troops
    0.10
     decree
    0.09
     Allies
    0.09
     offiziell
    0.08
     ঘোষণা
    0.08
     treaties
    0.08
     inmiddels
    0.08
     begrü
    0.08
     assure
    0.08
     proclam
    0.08
    Act Density 0.004%

    No Known Activations