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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     think
    -0.07
     나오
    -0.07
    这样做
    -0.07
    网友们
    -0.07
     fired
    -0.07
    Wik
    -0.06
     Voor
    -0.06
     forward
    -0.06
    แก
    -0.06
    Seriously
    -0.06
    POSITIVE LOGITS
    护栏
    0.07
    枢
    0.07
    rites
    0.07
     adhesive
    0.07
    竞争力
    0.07
    .transport
    0.07
    _every
    0.07
    capability
    0.07
    başı
    0.06
     pleasure
    0.06
    Act Density 0.001%

    No Known Activations