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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ())/
    -0.07
     trong
    -0.07
    _hist
    -0.07
    _control
    -0.06
    tea
    -0.06
    _CPP
    -0.06
    avian
    -0.06
     Brend
    -0.06
     mặt
    -0.06
    ustom
    -0.06
    POSITIVE LOGITS
     prepaid
    0.08
    .responseText
    0.06
     Hamburg
    0.06
    Inspectable
    0.06
    学会
    0.06
     ViewData
    0.06
    _ATTACH
    0.06
     Bangkok
    0.06
     hsv
    0.06
    packet
    0.06
    Act Density 0.112%

    No Known Activations