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

    Neuronpedia

    INDEX
    Explanations

    www

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енно
    -0.07
     Convert
    -0.07
     ignorant
    -0.07
    asuring
    -0.07
    ashion
    -0.07
    用力
    -0.07
    䗪
    -0.07
     deliberately
    -0.07
    .notification
    -0.07
    verting
    -0.07
    POSITIVE LOGITS
    Estimated
    0.06
     phủ
    0.06
    Os
    0.06
    -[
    0.06
     toi
    0.06
     battle
    0.06
    ock
    0.06
    odigo
    0.06
    .TryGetValue
    0.06
     priv
    0.06
    Act Density 0.014%

    No Known Activations