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

    Neuronpedia

    INDEX
    Explanations

    terminology related to government and its functions

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

    preceding abstract nouns

    np_acts-logits-general · gemini-2.0-flash

    qualifiers followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     playbook
    -0.81
     onboarding
    -0.81
    Referencie
    -0.81
     workflows
    -0.77
     demographics
    -0.77
     backstory
    -0.75
     impactful
    -0.75
     ویکی‌پدیای
    -0.74
     curated
    -0.72
     timelines
    -0.72
    POSITIVE LOGITS
     muß
    0.74
     daß
    0.72
     müßte
    0.68
     skall
    0.63
     läßt
    0.61
     mußte
    0.59
     Schluß
    0.58
     rôles
    0.57
     groote
    0.56
    faßt
    0.55
    Act Density 0.931%

    No Known Activations