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

    Neuronpedia

    INDEX
    Explanations

    robots

    np_max-act · gemini-2.0-flash

    mentions of Asimov's Laws of Robotics (references to the Three/Four Laws, "Laws", "robot", or "robotics").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    电解
    -0.07
    allery
    -0.07
    詳
    -0.07
    _TAG
    -0.07
    	bit
    -0.07
     ministry
    -0.07
    .modified
    -0.07
    曾經
    -0.07
    キング
    -0.07
    Yellow
    -0.07
    POSITIVE LOGITS
     �
    0.07
    ↡
    0.07
    ("&
    0.07
    .Predicate
    0.07
    classmethod
    0.07
     contiene
    0.07
    _OscInitStruct
    0.07
     الث
    0.07
    二字
    0.06
     horr
    0.06
    Act Density 0.490%

    No Known Activations