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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_max-act · gemini-2.0-flash

    The neuron lights up on German content words—mostly nouns (often capitalized) used in urban-planning/social-control contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fluctuations
    -0.06
     KING
    -0.06
     Max
    -0.06
     as
    -0.06
     ions
    -0.06
     organis
    -0.06
    .Mvc
    -0.06
    orado
    -0.06
     Rich
    -0.06
    ExecutionContext
    -0.06
    POSITIVE LOGITS
    :/
    0.07
    ━━━━━━━━━━━━━━━━
    0.07
    (other
    0.07
    _generated
    0.06
     soci
    0.06
     приблиз
    0.06
    	ch
    0.06
    
    0.06
     pseud
    0.06
    seud
    0.06
    Act Density 0.067%

    No Known Activations