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

    Neuronpedia

    INDEX
    Explanations

    concepts related to moral and ethical dilemmas in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    criminality, institutions, or harm

    np_acts-logits-general · gemini-2.0-flash

    criminal defense or admitting to drugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.66
    phany
    -0.63
     ECTS
    -0.63
    AnchorStyles
    -0.62
     acorns
    -0.61
    InstanceState
    -0.61
     fufficient
    -0.61
    IBOutlet
    -0.61
     ")");
    -0.59
     Himo
    -0.59
    POSITIVE LOGITS
     criminal
    0.55
    delmi
    0.51
    тистика
    0.51
     controversial
    0.51
     Nazi
    0.49
     mal
    0.48
     opp
    0.46
     pathological
    0.46
     harmful
    0.45
    srcs
    0.45
    Act Density 0.410%

    No Known Activations