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

    Neuronpedia

    INDEX
    Explanations

    attention

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of “attention” (particularly in the context of visual or cognitive attention).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    وري
    -0.07
     detected
    -0.07
    _freq
    -0.06
    .department
    -0.06
    fwrite
    -0.06
     tranquil
    -0.06
     disqualified
    -0.06
     =[
    -0.06
    -us
    -0.06
    .btnDelete
    -0.06
    POSITIVE LOGITS
    registration
    0.07
     Steven
    0.06
    Driver
    0.06
    argest
    0.06
     popul
    0.06
     Chow
    0.06
    (company
    0.06
    -sort
    0.06
     CMS
    0.06
    รก
    0.06
    Act Density 0.005%

    No Known Activations