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

    Neuronpedia

    INDEX
    Explanations

    current events/time sensitivity

    np_max-act · gemini-2.0-flash

    The neuron activates on the phrase indicating the model’s knowledge cutoff (e.g. “my knowledge cutoff”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     önce
    -0.06
     engineer
    -0.06
     pathogens
    -0.06
     Mol
    -0.06
    итися
    -0.06
    (inputStream
    -0.06
    	UN
    -0.06
     arc
    -0.06
    end
    -0.06
    .kind
    -0.06
    POSITIVE LOGITS
    MPI
    0.07
    jas
    0.07
    __
    0.07
    rovers
    0.07
    ouver
    0.07
     �
    0.07
    墓
    0.07
    riers
    0.06
    {}_
    0.06
    /services
    0.06
    Act Density 0.002%

    No Known Activations