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

    Neuronpedia

    INDEX
    Explanations

    Management positions

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of people’s job titles or professional roles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    试
    -0.07
    nota
    -0.06
    负责
    -0.06
    ystems
    -0.06
     adverse
    -0.06
    чин
    -0.06
     Browser
    -0.06
     Isles
    -0.06
    國
    -0.06
    เตอร
    -0.06
    POSITIVE LOGITS
     Associate
    0.07
     Gather
    0.07
    Move
    0.07
     cass
    0.07
     Added
    0.06
     listener
    0.06
     associate
    0.06
     ctl
    0.06
     sprint
    0.06
    _rb
    0.06
    Act Density 0.028%

    No Known Activations