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

    Neuronpedia

    INDEX
    Explanations

    grams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fell
    -0.08
    .Look
    -0.07
    Russ
    -0.07
    太子
    -0.07
     çok
    -0.07
     servicio
    -0.07
     llev
    -0.07
     CEO
    -0.06
     concurrent
    -0.06
    Coll
    -0.06
    POSITIVE LOGITS
     indica
    0.07
    SetFont
    0.07
    orget
    0.07
    =g
    0.06
     aaa
    0.06
    iban
    0.06
     програм
    0.06
    drawing
    0.06
    ToArray
    0.06
    金
    0.06
    Act Density 0.006%

    No Known Activations