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

    Neuronpedia

    INDEX
    Explanations

    balanced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Instance
    -0.08
     өт
    -0.07
    gren
    -0.07
    _Instance
    -0.07
    (listener
    -0.07
     Reflection
    -0.07
     Inst
    -0.07
     enje
    -0.07
    OLS
    -0.07
     Entry
    -0.07
    POSITIVE LOGITS
     dieta
    0.13
     nutritious
    0.12
     Ernährung
    0.11
     diet
    0.11
     ketogenic
    0.11
     diets
    0.10
    性生活
    0.10
     Mediterranean
    0.10
     vegan
    0.10
     meals
    0.10
    Act Density 0.011%

    No Known Activations