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

    Neuronpedia

    INDEX
    Explanations

    Marcus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     종
    -0.10
    sell
    -0.08
    ety
    -0.08
     away
    -0.07
     milk
    -0.07
     rõ
    -0.07
     thrill
    -0.07
    (items
    -0.07
    elight
    -0.07
     delighted
    -0.07
    POSITIVE LOGITS
    鼓
    0.07
    лас
    0.07
    <data
    0.07
     Marcus
    0.07
     A
    0.07
     כפי
    0.07
     bidi
    0.07
    总部
    0.07
     chuẩn
    0.07
    汽车产业
    0.06
    Act Density 0.003%

    No Known Activations