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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash

    capitalized jargon and proper nouns tied to technology/gaming and government/bureaucratic contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     खर
    -0.08
     advers
    -0.07
    itime
    -0.07
     masks
    -0.06
    Serialized
    -0.06
     Hebrew
    -0.06
     sugar
    -0.06
     lat
    -0.06
     goats
    -0.06
     сход
    -0.06
    POSITIVE LOGITS
     Costco
    0.06
    /div
    0.06
     originated
    0.06
     (~(
    0.06
    <?=
    0.06
    -Version
    0.06
    са
    0.06
    [strlen
    0.06
    ("(
    0.06
    eight
    0.06
    Act Density 0.529%

    No Known Activations