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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash

    This neuron detects references to page navigation or UI elements, especially phrases indicating where to find buttons or links (e.g. “on the right,” “top menu,” “left of the page”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     comunic
    -0.07
     spol
    -0.06
     Sext
    -0.06
    .unknown
    -0.06
    mr
    -0.06
     muit
    -0.06
     Satisfaction
    -0.06
     zá
    -0.06
    twitter
    -0.06
     indic
    -0.06
    POSITIVE LOGITS
    _partner
    0.06
     staged
    0.06
    (fig
    0.06
    Meal
    0.06
    enos
    0.06
    photo
    0.06
     Discovery
    0.06
    plate
    0.06
    .Block
    0.06
     густ
    0.06
    Act Density 0.010%

    No Known Activations