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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     độc
    -0.07
    医护
    -0.07
     الطبيعي
    -0.07
     true
    -0.07
    (entries
    -0.07
    endent
    -0.07
     retire
    -0.06
     Acc
    -0.06
    ᤓ
    -0.06
     knowledge
    -0.06
    POSITIVE LOGITS
    حاول
    0.08
    롄
    0.07
    ᛅ
    0.07
     forcefully
    0.07
    挛
    0.07
    苞
    0.07
    зов
    0.07
    ло
    0.07
    ЛЕ
    0.07
    _ax
    0.07
    Act Density 0.001%

    No Known Activations