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

    Neuronpedia

    INDEX
    Explanations

    individual liberty, limited government

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⅲ
    0.40
    嗉
    0.40
    multilayer
    0.39
    makedirs
    0.38
    idded
    0.38
    signup
    0.38
    sensitivity
    0.38
    育成
    0.37
     PSB
    0.37
     capaces
    0.37
    POSITIVE LOGITS
     libertarian
    0.76
     Libert
    0.76
     libert
    0.59
     Privacy
    0.55
     Decentral
    0.47
     Peaceful
    0.47
     Thoreau
    0.47
    Privacy
    0.47
     Liberty
    0.47
     Peace
    0.46
    Act Density 0.061%

    No Known Activations