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

    Neuronpedia

    INDEX
    Explanations

    not real

    np_max-act · gemini-2.0-flash

    This neuron activates on words indicating simulated or virtual experiences (e.g., “virtual,” “simulation,” “mock”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     President
    -0.07
    Changed
    -0.07
     appending
    -0.07
    .Bold
    -0.06
    omnia
    -0.06
    _read
    -0.06
    _home
    -0.06
     president
    -0.06
     wow
    -0.06
    企業
    -0.06
    POSITIVE LOGITS
    Styled
    0.07
     Berm
    0.06
    KIT
    0.06
     mini
    0.06
    ��
    0.06
    
    0.06
     fict
    0.06
    nearest
    0.06
    	bar
    0.06
    _INFINITY
    0.06
    Act Density 0.035%

    No Known Activations