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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     élè
    -0.07
     bless
    -0.07
    网络传播
    -0.07
     È
    -0.07
    _Select
    -0.07
     предлаг
    -0.06
    职业道德
    -0.06
    ˯
    -0.06
    谞
    -0.06
     Osmanlı
    -0.06
    POSITIVE LOGITS
     hospital
    0.07
     responsibly
    0.07
    在一起
    0.07
     multic
    0.07
     Association
    0.07
    엎
    0.07
    trip
    0.06
    app
    0.06
    las
    0.06
    .container
    0.06
    Act Density 0.009%

    No Known Activations