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

    Neuronpedia

    INDEX
    Explanations

    following orders

    np_max-act · gemini-2.0-flash

    The neuron fires on words that denote submission to commands or control—terms like “commands,” “obedient,” “puppet,” “bidding,” “do,” and “obeying.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     возможно
    -0.06
     leaking
    -0.06
     dedication
    -0.06
     Arbeit
    -0.06
    veloper
    -0.06
     backlash
    -0.06
    ArgumentNullException
    -0.06
    .ul
    -0.06
    .range
    -0.06
    .part
    -0.06
    POSITIVE LOGITS
    [__
    0.08
     hö
    0.07
    .Publish
    0.07
    Eastern
    0.07
    koli
    0.06
     coz
    0.06
    acie
    0.06
    650
    0.06
     Heaven
    0.06
    虫
    0.06
    Act Density 0.040%

    No Known Activations