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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming company functions, departments, or roles (e.g. R & D, development, marketing, distribution, engineers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Client
    -0.07
    /ts
    -0.06
     статус
    -0.06
     frase
    -0.06
     potentials
    -0.06
     मल
    -0.06
     کام
    -0.06
    �
    -0.06
    御
    -0.06
     jade
    -0.06
    POSITIVE LOGITS
     or
    0.07
    ctx
    0.07
     dnes
    0.06
    ...,
    0.06
    |)↵
    0.06
    ευ
    0.06
    SystemService
    0.06
     ()↵
    0.06
     і
    0.06
    ictured
    0.06
    Act Density 0.075%

    No Known Activations