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

    Neuronpedia

    INDEX
    Explanations

    allies

    np_max-act · gemini-2.0-flash

    The neuron flags tokens pertaining to military or security contexts (e.g. “military,” “drills,” “security,” “allies,” “war”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     proposal
    -0.08
    /devices
    -0.07
    xff
    -0.07
     separator
    -0.07
     Кар
    -0.07
     équip
    -0.06
    _OPTS
    -0.06
    duce
    -0.06
    -built
    -0.06
     Sect
    -0.06
    POSITIVE LOGITS
    .misc
    0.07
     공동
    0.06
    _HAND
    0.06
    ео
    0.06
    _Column
    0.06
    主義
    0.06
    	obj
    0.06
    �
    0.06
     khoảng
    0.06
    ////////////////////////////////////////////////////////////////////
    0.06
    Act Density 0.018%

    No Known Activations