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

    Neuronpedia

    INDEX
    Explanations

    Providing an estimate

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     англий
    -0.08
    ㄌ
    -0.07
     borrowing
    -0.07
    _CF
    -0.07
    "]).
    -0.07
    嘟
    -0.07
    หลวง
    -0.07
    合伙
    -0.07
    _bo
    -0.07
    ']).
    -0.07
    POSITIVE LOGITS
    脆
    0.08
    emit
    0.07
    复杂
    0.07
    點
    0.07
     elect
    0.07
     poss
    0.06
     узнать
    0.06
    Ỉ
    0.06
    screen
    0.06
     tìm
    0.06
    Act Density 0.263%

    No Known Activations