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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “dia” (day) and related time-of-day references in the Portuguese text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     grandparents
    -0.07
    ETIME
    -0.07
    객
    -0.07
     Joined
    -0.07
     smokers
    -0.07
    ロ
    -0.07
     Kinect
    -0.06
     Kush
    -0.06
    ственное
    -0.06
     Dah
    -0.06
    POSITIVE LOGITS
     vám
    0.07
     blanks
    0.07
     Holds
    0.07
     insurgents
    0.07
     полностью
    0.06
     blí
    0.06
    .getWriter
    0.06
    ))/(
    0.06
     nouvelle
    0.06
     دنی
    0.06
    Act Density 0.043%

    No Known Activations