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

    Neuronpedia

    INDEX
    Explanations

    Kant and moral philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RST
    -0.08
    _USED
    -0.08
     Chavez
    -0.08
    Bil
    -0.08
    _DEVICE
    -0.08
     сним
    -0.08
    _COPY
    -0.08
    pdev
    -0.08
     Tenerife
    -0.08
    设备
    -0.08
    POSITIVE LOGITS
     moral
    0.11
     morality
    0.11
     ethical
    0.11
     uphold
    0.10
     obligation
    0.10
     obligations
    0.10
     adherence
    0.09
     duty
    0.09
    ethical
    0.09
     justice
    0.09
    Act Density 0.003%

    No Known Activations