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

    Neuronpedia

    INDEX
    Explanations

    tutorials and guides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     दश
    -0.08
    urry
    -0.08
    feito
    -0.08
     നടത്തിയ
    -0.07
     kidnapping
    -0.07
     decades
    -0.07
     подвер
    -0.07
    rxjs
    -0.07
     unem
    -0.07
    isë
    -0.07
    POSITIVE LOGITS
     familiarize
    0.13
     tutorials
    0.12
     Tutorials
    0.11
    Tutorial
    0.11
    教程
    0.11
     použí
    0.11
     tutorial
    0.11
    Basics
    0.11
     basics
    0.10
     fonctionnalités
    0.10
    Act Density 0.104%

    No Known Activations