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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Route
    -0.07
    IMITER
    -0.06
    alement
    -0.06
     unsure
    -0.06
    螣
    -0.06
    加快建设
    -0.06
    越大
    -0.06
     regelmäßig
    -0.06
    áo
    -0.06
    mpl
    -0.06
    POSITIVE LOGITS
    роб
    0.07
    stras
    0.07
    �
    0.07
    台阶
    0.07
     político
    0.06
     ст
    0.06
    ﮌ
    0.06
    rod
    0.06
     stand
    0.06
    match
    0.06
    Act Density 0.008%

    No Known Activations