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

    Neuronpedia

    INDEX
    Explanations

    connecting ideas

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of political systems or ideologies (e.g., democracy, dictatorship, communism, free enterprise).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    905
    -0.08
     pixmap
    -0.07
    broadcast
    -0.06
     judges
    -0.06
     letters
    -0.06
    olerance
    -0.06
     nb
    -0.06
    according
    -0.06
    applications
    -0.06
    _ALIAS
    -0.06
    POSITIVE LOGITS
    кість
    0.07
     stal
    0.07
    ليات
    0.07
    чается
    0.07
    quent
    0.07
    quete
    0.06
    /views
    0.06
     ребенок
    0.06
     materia
    0.06
    шила
    0.06
    Act Density 0.016%

    No Known Activations