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

    Neuronpedia

    INDEX
    Explanations

    iam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exclusive
    -0.07
    щее
    -0.06
     Reject
    -0.06
     서울특별시
    -0.06
    鉄
    -0.06
     infiltration
    -0.06
    asd
    -0.06
    碎
    -0.06
     infographic
    -0.06
    ัตถ
    -0.06
    POSITIVE LOGITS
    forms
    0.07
    .baomidou
    0.07
    (da
    0.07
    /com
    0.06
    ,proto
    0.06
    ourced
    0.06
     slammed
    0.06
     Ath
    0.06
     Αν
    0.06
    冠
    0.06
    Act Density 0.001%

    No Known Activations