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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    text related to recommendation systems, specifically focusing on collaborative filtering and how user preferences are assessed.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on phrases describing a product–customer interaction—specifically tokens in the standard “product being viewed or purchased by a customer” construction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    father
    -0.07
    질
    -0.07
    indi
    -0.06
    vides
    -0.06
    lerdir
    -0.06
    泊
    -0.06
    一覧
    -0.06
    ture
    -0.06
     kê
    -0.06
    Scientists
    -0.06
    POSITIVE LOGITS
     updates
    0.07
     updated
    0.06
     rebuild
    0.06
    惊
    0.06
    _COLL
    0.06
     insights
    0.06
    (updated
    0.06
     PF
    0.06
    720
    0.06
    30
    0.06
    Act Density 0.061%

    No Known Activations