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

    Neuronpedia

    INDEX
    Explanations

    Negative outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     correspondiente
    -0.08
    。今年
    -0.08
    -0.08
     Puis
    -0.08
    δοση
    -0.07
     Inver
    -0.07
     since
    -0.07
     puisque
    -0.07
     ayudarte
    -0.07
     cientos
    -0.07
    POSITIVE LOGITS
    árias
    0.09
    +l
    0.08
     Warehouse
    0.08
     innebär
    0.08
    +w
    0.07
    nake
    0.07
     Reception
    0.07
    ిస్త
    0.07
     مشکلات
    0.07
     پیم
    0.07
    Act Density 0.086%
    No Known Activations